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

    Neuronpedia

    INDEX
    Explanations

    starts of technical or descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जैसे
    0.31
    ுகளை
    0.30
    ския
    0.29
    जैसे
    0.28
     Bumi
    0.27
     Asht
    0.27
     የተ
    0.27
     morally
    0.27
    ዎች
    0.25
    之间的
    0.25
    POSITIVE LOGITS
    ronomie
    0.36
    etc
    0.31
    uarine
    0.29
    marca
    0.29
    ig
    0.28
    creative
    0.28
    prefer
    0.28
    fed
    0.28
    idescent
    0.28
    orescent
    0.28
    Act Density 0.219%

    No Known Activations