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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あらゆる
    0.72
     sämt
    0.64
     inaccuracies
    0.63
     bashing
    0.62
     जमकर
    0.60
     alterações
    0.60
     allerlei
    0.60
    जिस
    0.60
     contou
    0.60
    ッシング
    0.60
    POSITIVE LOGITS
    ?
    2.64
    ？
    2.52
    ؟
    2.38
    ?"
    2.20
    ?\
    2.16
    ?)
    2.13
    ?).
    2.13
    ?</
    2.11
    ?]
    2.09
    ?",
    2.03
    Act Density 0.489%

    No Known Activations