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

    Neuronpedia

    INDEX
    Explanations

    News articles and formal texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    츠
    -0.07
    .AWS
    -0.07
    (Room
    -0.07
    ?><
    -0.07
    xBE
    -0.06
     всю
    -0.06
    ;base
    -0.06
    >This
    -0.06
    -х
    -0.06
    Ä
    -0.06
    POSITIVE LOGITS
     вик
    0.07
     Reduced
    0.07
     ви
    0.06
     gon
    0.06
    .zone
    0.06
    必须
    0.06
     excit
    0.06
    aging
    0.06
     beneficial
    0.06
     Many
    0.06
    Act Density 0.000%

    No Known Activations