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

    Neuronpedia

    INDEX
    Explanations

    Announcements of future content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VAR
    -0.08
     حذ
    -0.07
     oficial
    -0.07
     Martinez
    -0.07
     زمین
    -0.07
    GROUP
    -0.07
    .Normalize
    -0.06
     Mu
    -0.06
    UTO
    -0.06
     starter
    -0.06
    POSITIVE LOGITS
    price
    0.08
    .comp
    0.07
     HOH
    0.06
    .reflect
    0.06
     Calibration
    0.06
     возрасте
    0.06
    -many
    0.05
    ouple
    0.05
    erties
    0.05
     شود
    0.05
    Act Density 0.070%

    No Known Activations