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

    Neuronpedia

    INDEX
    Explanations

    identification and initial stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Subsequent
    0.84
     footnote
    0.84
    ต่อ
    0.77
     subsequent
    0.77
     ಪ್ರಯತ್ನ
    0.77
     interpolate
    0.77
     sexuales
    0.74
     supplementation
    0.72
    TempVal
    0.72
     posteriores
    0.71
    POSITIVE LOGITS
     Identification
    1.03
    Identification
    0.99
     Pre
    0.97
    Identify
    0.96
    事前
    0.96
    Pre
    0.93
     gathering
    0.92
     Identify
    0.92
    ident
    0.91
    Pré
    0.91
    Act Density 0.570%

    No Known Activations