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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spent
    0.44
     Homo
    0.38
     pron
    0.37
    टकों
    0.37
     scores
    0.37
     educativos
    0.36
     relig
    0.35
     sweat
    0.35
    ारों
    0.35
     infancy
    0.35
    POSITIVE LOGITS
    -
    0.52
    Another
    0.42
    スーパー
    0.40
     टू
    0.38
    hale
    0.36
    損
    0.36
    Li
    0.36
    _
    0.36
    imgur
    0.36
    ファミリー
    0.36
    Act Density 0.000%

    No Known Activations