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

    Neuronpedia

    INDEX
    Explanations

    truth and falsehood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কাতর
    0.73
     Brows
    0.71
    itié
    0.69
    Browsable
    0.64
    Tokens
    0.63
     ώ
    0.63
    ൺലൈ
    0.61
    逡
    0.60
    ಿಸ
    0.60
    морфи
    0.60
    POSITIVE LOGITS
     false
    3.26
     truth
    3.07
     untrue
    3.02
     inaccurate
    2.97
    false
    2.97
     falsehood
    2.97
     False
    2.92
     FALSE
    2.83
    False
    2.83
    truth
    2.78
    Act Density 1.573%

    No Known Activations