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

    Neuronpedia

    INDEX
    Explanations

    publication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optimistic
    -0.06
     nada
    -0.06
     qc
    -0.06
     경북
    -0.06
     Checks
    -0.05
    interpre
    -0.05
    unicorn
    -0.05
     insisting
    -0.05
    \uff
    -0.05
     никто
    -0.05
    POSITIVE LOGITS
    ,arr
    0.07
    .ajax
    0.07
     networks
    0.07
    ))(
    0.06
    Battery
    0.06
    .Info
    0.06
     青
    0.06
    _matrices
    0.06
    mae
    0.06
    umat
    0.06
    Act Density 0.001%

    No Known Activations