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

    Neuronpedia

    INDEX
    Explanations

    happy hour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.75
    shaus
    0.68
    nih
    0.65
    <0x0D>
    0.63
    Ｆ
    0.62
    हून
    0.61
    hashes
    0.61
    σεις
    0.60
    hores
    0.60
    matically
    0.59
    POSITIVE LOGITS
    g
    0.75
    ).
    0.60
    ع
    0.60
    h
    0.59
    芗
    0.56
     pouce
    0.55
    ע
    0.55
    لي
    0.55
     político
    0.55
     polity
    0.55
    Act Density 0.000%

    No Known Activations