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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alice
    -0.07
    โจ
    -0.06
    alsa
    -0.06
    Vertex
    -0.06
     жест
    -0.06
     LO
    -0.06
     momentos
    -0.06
    にか
    -0.06
     adım
    -0.06
     coalition
    -0.06
    POSITIVE LOGITS
    (ps
    0.07
     Pharm
    0.07
     tisíc
    0.06
     información
    0.06
     фундамент
    0.06
    ­tion
    0.06
     spons
    0.06
     rw
    0.06
     ؟
    0.06
    =fopen
    0.06
    Act Density 0.003%

    No Known Activations