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

    Neuronpedia

    INDEX
    Explanations

    conditional sentences and explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necesita
    0.48
     ventaja
    0.48
     nevoie
    0.47
     είναι
    0.46
     potř
    0.45
     tě
    0.44
     guérison
    0.44
     νέ
    0.43
     useParams
    0.43
     necesitan
    0.43
    POSITIVE LOGITS
    mandatory
    0.47
    regarding
    0.47
    сад
    0.47
    ми
    0.45
    which
    0.45
    statistical
    0.45
    ста
    0.44
    за
    0.44
    sat
    0.44
    sur
    0.42
    Act Density 0.000%

    No Known Activations