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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    齐全
    -0.07
    ="""
    -0.07
    ('('
    -0.07
     COURT
    -0.07
     <![
    -0.07
    _helper
    -0.07
    🏰
    -0.07
    打听
    -0.06
    _present
    -0.06
    pars
    -0.06
    POSITIVE LOGITS
    Ab
    0.07
    铆
    0.07
    קבל
    0.07
     Injection
    0.07
    ibel
    0.07
     إنه
    0.07
    同樣
    0.07
    olith
    0.07
     метал
    0.07
    rance
    0.07
    Act Density 0.009%

    No Known Activations