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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    This neuron fires on mathematical terminology and notation—e.g. words like “ways,” “resolved,” “ordered,” “pairs,” parentheses, operators, and other formulaic tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     if
    -0.07
    enght
    -0.07
    .small
    -0.07
    raz
    -0.06
    inte
    -0.06
    Fil
    -0.06
    .nii
    -0.06
     genetics
    -0.06
    沿
    -0.06
     initiate
    -0.06
    POSITIVE LOGITS
    vtk
    0.06
     объем
    0.06
    京
    0.05
    phies
    0.05
    _PCM
    0.05
     ван
    0.05
     CPF
    0.05
     ipad
    0.05
     Rangers
    0.05
    범
    0.05
    Act Density 0.016%

    No Known Activations