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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。これ
    -0.07
    レビ
    -0.07
    찮
    -0.07
    シュ
    -0.07
    "h
    -0.07
    ηρε
    -0.06
     zien
    -0.06
     returned
    -0.06
    .Rem
    -0.06
    .embed
    -0.06
    POSITIVE LOGITS
     ا
    0.07
     bran
    0.07
     '}';↵
    0.06
    (`↵
    0.06
    な
    0.06
     bisexual
    0.06
    ');↵↵↵↵
    0.06
     fert
    0.06
    isma
    0.06
     LPARAM
    0.06
    Act Density 0.051%

    No Known Activations