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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (CultureInfo
    -0.08
    署
    -0.07
     Paperback
    -0.07
     cooldown
    -0.06
     oppressive
    -0.06
     agony
    -0.06
    바이
    -0.06
    phabet
    -0.06
     Emit
    -0.06
    弾
    -0.06
    POSITIVE LOGITS
    nému
    0.07
     zum
    0.07
     Scient
    0.07
     ao
    0.06
    .dp
    0.06
     into
    0.06
    .department
    0.06
    _SYSTEM
    0.06
     Hutch
    0.06
    Focused
    0.06
    Act Density 0.026%

    No Known Activations