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

    Neuronpedia

    INDEX
    Explanations

    URLs with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fireplace
    0.82
    ers
    0.80
    이야
    0.76
    ποτε
    0.73
     souha
    0.71
    린
    0.71
    jsxFileName
    0.70
    กา
    0.69
    ac
    0.69
    startDate
    0.69
    POSITIVE LOGITS
     artificial
    0.86
     neither
    0.86
    否
    0.86
     ''
    0.85
     biological
    0.85
     suhu
    0.83
     others
    0.83
     other
    0.82
     faux
    0.81
     amino
    0.81
    Act Density 0.003%

    No Known Activations