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

    Neuronpedia

    INDEX
    Explanations

    asterisk/hashtag

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    criptions
    -0.06
     thọ
    -0.06
     toastr
    -0.06
     c
    -0.06
    ‐‐
    -0.06
    ',
    -0.06
     Converts
    -0.06
    武
    -0.06
     สล
    -0.06
     DWORD
    -0.06
    POSITIVE LOGITS
    .rate
    0.07
    .Se
    0.07
     знаю
    0.07
     nb
    0.07
    _ty
    0.07
     harmonic
    0.06
    })}↵
    0.06
    这一
    0.06
     plaintext
    0.06
    لت
    0.06
    Act Density 0.001%

    No Known Activations