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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mir
    -0.07
    vek
    -0.07
     Protective
    -0.07
     embarked
    -0.06
    tolower
    -0.06
    カー
    -0.06
     moc
    -0.06
     Fell
    -0.06
    wear
    -0.06
     Cara
    -0.06
    POSITIVE LOGITS
     userdata
    0.07
    单
    0.06
     espec
    0.06
     тех
    0.06
    Playable
    0.06
    0.06
     القي
    0.06
    (hwnd
    0.06
    -terrorism
    0.06
     Buchanan
    0.06
    Act Density 0.016%

    No Known Activations