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

    Neuronpedia

    INDEX
    Explanations

    specifying conditions or locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िटल
    0.47
    рье
    0.42
     čtyř
    0.40
     состоит
    0.39
    ალა
    0.39
    ارهای
    0.39
    कामा
    0.38
    터
    0.38
    िशनर
    0.38
     pituitary
    0.38
    POSITIVE LOGITS
    を用いて
    0.39
    querySelector
    0.38
    <0x1C>
    0.38
    '));
    0.37
    q
    0.37
    wn
    0.36
    fid
    0.36
    Fin
    0.35
    jah
    0.35
    acl
    0.35
    Act Density 0.012%

    No Known Activations