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

    Neuronpedia

    INDEX
    Explanations

    making it to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يين
    0.92
    गारी
    0.82
     superposition
    0.82
    pulumi
    0.79
    𝗸
    0.78
     memorandum
    0.77
     displacing
    0.77
    ্রয়
    0.76
     Мор
    0.76
    ʖ
    0.76
    POSITIVE LOGITS
    ruc
    0.82
    ffe
    0.81
    w
    0.79
     Contrary
    0.78
    ot
    0.77
    os
    0.74
    ek
    0.73
     योग्य
    0.72
    es
    0.71
    henes
    0.70
    Act Density 0.025%

    No Known Activations