Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    narrative elements involving magical transformations or alterations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words involved in stating spatial relationships and locations (e.g. describing an object’s position “X is on/in Y”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Decoder
    -0.07
    _opt
    -0.07
     expectation
    -0.06
     bird
    -0.06
     trop
    -0.06
    plings
    -0.06
    (iterator
    -0.06
    kf
    -0.06
    нос
    -0.06
    POSITIVE LOGITS
    '&&
    0.06
    олева
    0.06
    .clean
    0.06
     feud
    0.06
     wirk
    0.06
    .LAZY
    0.06
    elop
    0.06
    _trampoline
    0.06
     pokrač
    0.06
     Lands
    0.06
    Act Density 0.198%

    No Known Activations