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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens, especially decimal‐number fragments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    xing
    -0.07
    isce
    -0.07
    ervention
    -0.07
     ورد
    -0.07
     pix
    -0.07
     Govern
    -0.07
     yg
    -0.07
    ча
    -0.06
     histor
    -0.06
     Ard
    -0.06
    POSITIVE LOGITS
     HEAP
    0.07
    As
    0.06
     &=
    0.06
    *:
    0.06
    .Roles
    0.06
    plaint
    0.06
    (A
    0.06
     cou
    0.06
    
    0.06
    _VOLUME
    0.06
    Act Density 0.015%

    No Known Activations