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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash

    code snippets related to user interface components.

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

    The neuron spikes on the Objective-C keyword “class” (i.e. class declarations in the dumped headers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ub
    -0.08
    LG
    -0.07
    (volume
    -0.07
    osg
    -0.07
     infl
    -0.07
     LG
    -0.07
     Injection
    -0.07
     ardından
    -0.07
     venez
    -0.07
    Sand
    -0.07
    POSITIVE LOGITS
     <?=$
    0.07
    ον
    0.06
     disgu
    0.06
     devoted
    0.06
    OptionsItemSelected
    0.06
     стан
    0.06
    luğu
    0.06
    .getLength
    0.06
     Tage
    0.06
    렌
    0.06
    Act Density 0.001%

    No Known Activations