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

    Neuronpedia

    INDEX
    Explanations

    documentation, entities, categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.63
     fertil
    0.61
     subsid
    0.61
    ,
    0.60
     a
    0.59
     steril
    0.57
    ।
    0.57
    ט
    0.55
     fluores
    0.55
    지의
    0.55
    POSITIVE LOGITS
    1
    1.05
    ik
    0.94
    and
    0.87
     and
    0.84
    o
    0.80
    ه
    0.80
    و
    0.73
    на
    0.69
    <0x0D>
    0.68
    া
    0.66
    Act Density 2.314%

    No Known Activations