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

    Neuronpedia

    INDEX
    Explanations

    Hillary Clinton and glossary of terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.33
     It
    0.83
    lo
    0.77
    pathy
    0.70
    virk
    0.66
    man
    0.65
    gence
    0.64
    ymmetry
    0.64
    scaling
    0.63
    hape
    0.63
    POSITIVE LOGITS
    تي
    1.06
    and
    0.97
    К
    0.96
     prennent
    0.96
    та
    0.93
     toBe
    0.91
    <unused555>
    0.90
     toDo
    0.88
    هاي
    0.88
    <unused2186>
    0.88
    Act Density 0.002%

    No Known Activations