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

    Neuronpedia

    INDEX
    Explanations

    css properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ill
    0.63
    .\
    0.60
    said
    0.59
    il
    0.58
    ,"
    0.58
    ."""
    0.55
    ,”
    0.55
    fed
    0.55
    "],"
    0.54
     AT
    0.54
    POSITIVE LOGITS
    و
    0.81
    ام
    0.66
    心脏
    0.57
    ו
    0.57
    嚧
    0.56
     copertura
    0.55
     mandala
    0.54
    綣
    0.54
    ూర్
    0.53
     ס
    0.52
    Act Density 0.001%

    No Known Activations