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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ext
    -0.07
    _AC
    -0.06
    ्तर
    -0.06
     sustaining
    -0.06
    株式会社
    -0.06
     입
    -0.06
    azı
    -0.06
    _In
    -0.06
     lect
    -0.06
     extrav
    -0.06
    POSITIVE LOGITS
     Driver
    0.06
     Nurse
    0.06
    developer
    0.06
    .gms
    0.06
    linky
    0.06
    archical
    0.06
    =======↵
    0.06
    σο
    0.06
     Actor
    0.06
    dění
    0.06
    Act Density 0.000%

    No Known Activations