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

    Neuronpedia

    INDEX
    Explanations

    options, technical, science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sympathetic
    0.54
     Papad
    0.48
    更能
    0.47
     Vogt
    0.47
     kampung
    0.45
     permanece
    0.45
     paramilitary
    0.45
    য্
    0.45
    ipheral
    0.45
    を迎
    0.45
    POSITIVE LOGITS
     of
    0.47
    Manager
    0.46
    .
    0.44
     Revealed
    0.43
    lust
    0.42
    पंजाब
    0.42
    st
    0.41
     javax
    0.41
    ES
    0.41
     інші
    0.41
    Act Density 0.000%

    No Known Activations