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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不得不
    -0.08
     forward
    -0.08
    ady
    -0.07
     adv
    -0.07
    ark
    -0.07
     santé
    -0.07
     road
    -0.07
    orial
    -0.07
     ws
    -0.07
    積
    -0.07
    POSITIVE LOGITS
    #else
    0.08
    ChangedEventArgs
    0.08
     Jos
    0.07
    ">-->↵
    0.07
    🍤
    0.07
     insanity
    0.07
    AndView
    0.07
     Reyn
    0.07
    /sub
    0.07
    绠
    0.07
    Act Density 0.016%

    No Known Activations