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

    Neuronpedia

    INDEX
    Explanations

    terms and agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     squiggle
    0.45
     childnya
    0.44
     solche
    0.42
     hasilnya
    0.42
    ləşdir
    0.42
     njihov
    0.42
     shabd
    0.42
     მათი
    0.41
     formatos
    0.41
     matériau
    0.40
    POSITIVE LOGITS
    is
    0.52
     –
    0.46
    ↵
    0.44
     -
    0.44
    over
    0.43
    *
    0.42
    ud
    0.42
    pre
    0.42
     or
    0.41
     is
    0.41
    Act Density 0.001%

    No Known Activations