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

    Neuronpedia

    INDEX
    Explanations

    calling functions with get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dotted
    0.88
    Once
    0.80
    OCKS
    0.79
     exhaustion
    0.78
    vary
    0.78
    ēng
    0.78
    phant
    0.77
     गांठ
    0.77
     selfishness
    0.77
     deficiency
    0.77
    POSITIVE LOGITS
     rid
    1.55
    ters
    1.04
    sizeof
    1.02
     Hold
    0.99
     RID
    0.98
    Rid
    0.96
    정보
    0.95
     Rid
    0.94
     hold
    0.92
     stuck
    0.92
    Act Density 0.100%

    No Known Activations