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

    Neuronpedia

    INDEX
    Explanations

    parenthetical explanations and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uest
    0.46
    <unused330>
    0.45
    reuse
    0.43
    yielding
    0.42
    ٤
    0.42
    hall
    0.42
    ئا
    0.41
    érrez
    0.41
     ១
    0.41
    fullscreen
    0.40
    POSITIVE LOGITS
     lipoproteins
    0.51
     knowledge
    0.50
     consonants
    0.50
     factors
    0.49
     creators
    0.49
     products
    0.49
     thinkers
    0.48
     consonant
    0.48
     matter
    0.48
     inflection
    0.48
    Act Density 0.000%

    No Known Activations