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

    Neuronpedia

    INDEX
    Explanations

    your request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uettes
    0.77
    usian
    0.75
    vite
    0.73
    肠
    0.73
    ூட்
    0.71
    ব্যব
    0.71
    mfrac
    0.70
     Humming
    0.70
     जीरो
    0.70
    Vega
    0.69
    POSITIVE LOGITS
    stin
    0.64
     high
    0.63
     formal
    0.60
     formally
    0.60
    ഞ്
    0.59
     expert
    0.58
     Formal
    0.58
    の詳細
    0.58
     odd
    0.58
     fascinating
    0.57
    Act Density 0.005%

    No Known Activations