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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    科
    -0.07
     Sell
    -0.06
     olig
    -0.06
     Wohn
    -0.06
    Payload
    -0.06
     уник
    -0.06
    .ForegroundColor
    -0.06
     nurture
    -0.06
     hurts
    -0.06
    CC
    -0.06
    POSITIVE LOGITS
    กร
    0.06
    Asian
    0.06
     الخام
    0.06
     метал
    0.06
    рия
    0.06
    OOSE
    0.06
    يران
    0.05
    ritable
    0.05
    [S
    0.05
    [G
    0.05
    Act Density 0.013%

    No Known Activations