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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ymph
    -0.07
     reconcile
    -0.06
    Pokud
    -0.06
    Mah
    -0.06
    υγ
    -0.06
    ský
    -0.06
    .startTime
    -0.06
    Founded
    -0.06
    za
    -0.06
    regular
    -0.06
    POSITIVE LOGITS
     Mona
    0.07
     ):↵
    0.07
    IDD
    0.07
     killers
    0.06
     drain
    0.06
    聘
    0.06
     ön
    0.06
    utc
    0.06
     filtro
    0.06
     المك
    0.06
    Act Density 0.022%

    No Known Activations