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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     R
    -0.07
    作用
    -0.07
    umo
    -0.07
    switch
    -0.07
    wk
    -0.07
     reversal
    -0.07
    element
    -0.07
     example
    -0.07
    �
    -0.07
    818
    -0.07
    POSITIVE LOGITS
    GetX
    0.06
    .World
    0.06
    _NUM
    0.06
     Volunteers
    0.06
     Addr
    0.06
     ".");↵
    0.06
     Narr
    0.06
     Ner
    0.06
     GOD
    0.06
     Guns
    0.06
    Act Density 0.821%

    No Known Activations