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

    Neuronpedia

    INDEX
    Explanations

    pieces of text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Molecules
    0.73
     Vegetables
    0.72
     Ma
    0.69
     U
    0.69
    х
    0.69
     ఇన్
    0.66
    ν
    0.66
     drugs
    0.64
     Ce
    0.63
     pro
    0.63
    POSITIVE LOGITS
    ꔰ
    0.85
    Οι
    0.84
    PlatformImage
    0.83
    Proyecto
    0.82
    örer
    0.81
    iembre
    0.80
    таю
    0.80
    朼
    0.80
    ColorBit
    0.79
    海军
    0.79
    Act Density 0.003%

    No Known Activations