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

    Neuronpedia

    INDEX
    Explanations

    anti

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lucene
    -0.07
    lep
    -0.07
    Num
    -0.06
     sobie
    -0.06
    openssl
    -0.06
    вается
    -0.06
     Abby
    -0.06
     dét
    -0.06
    xDE
    -0.06
    .getMonth
    -0.06
    POSITIVE LOGITS
    兄弟
    0.07
     с
    0.07
    _ctx
    0.07
     AF
    0.07
    TN
    0.07
     р
    0.06
    들이
    0.06
    шими
    0.06
    (userData
    0.06
    _sk
    0.06
    Act Density 0.006%

    No Known Activations