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

    Neuronpedia

    INDEX
    Explanations

    honest or honesty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.10
    다라고
    1.09
    In
    1.08
    و
    1.00
    다
    0.95
     In
    0.94
    im
    0.93
    다음
    0.92
     \
    0.91
    ो
    0.91
    POSITIVE LOGITS
    ма
    1.21
    6
    0.94
    ia
    0.88
    7
    0.88
    с
    0.88
     honesty
    0.87
     οποίο
    0.86
    3
    0.84
     concave
    0.82
     funcional
    0.80
    Act Density 0.019%

    No Known Activations