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

    Neuronpedia

    INDEX
    Explanations

    written comments/notes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liberals
    -0.08
     مناسب
    -0.06
    收入
    -0.06
     Literature
    -0.06
    تمر
    -0.06
     attack
    -0.06
     submar
    -0.06
     oversight
    -0.06
    _effect
    -0.06
    .acc
    -0.06
    POSITIVE LOGITS
    Invocation
    0.08
     &[
    0.08
    (PDO
    0.07
     getMenu
    0.07
    _insn
    0.07
    /__
    0.07
     Savaşı
    0.07
    ................
    0.07
     Dynamo
    0.06
     Malaysian
    0.06
    Act Density 0.022%

    No Known Activations