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

    Neuronpedia

    INDEX
    Explanations

    ethical use track

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    showHeader
    0.42
    veloped
    0.40
    facts
    0.40
     INPUT
    0.39
     Talk
    0.39
     Angle
    0.39
     Input
    0.39
    انی
    0.38
     inputs
    0.38
     கிடைத்தது
    0.38
    POSITIVE LOGITS
    衣
    0.42
     attentes
    0.38
    ͌
    0.37
    Variant
    0.36
    randrange
    0.36
    われている
    0.36
     chín
    0.36
     críticos
    0.35
     Variants
    0.35
    あなたの
    0.35
    Act Density 0.003%

    No Known Activations