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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens and mathematical expressions, i.e. digits, numbers, and arithmetic/formula syntax.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lc
    -0.08
     DAO
    -0.07
     Lovely
    -0.06
    лит
    -0.06
     arrogant
    -0.06
     commenter
    -0.06
    _df
    -0.06
     WF
    -0.06
     flu
    -0.06
    'autres
    -0.06
    POSITIVE LOGITS
     mysl
    0.07
    Kon
    0.06
    Thrown
    0.06
     skoro
    0.06
     
    0.06
     IDM
    0.06
     thrive
    0.06
    /message
    0.06
    quiv
    0.06
     mệ
    0.06
    Act Density 0.012%

    No Known Activations