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

    Neuronpedia

    INDEX
    Explanations

    describes situations and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     перевод
    0.45
    ాత
    0.44
     Сте
    0.44
     Lanc
    0.42
     rearrangements
    0.42
     ввод
    0.41
     নও
    0.41
    >>;
    0.41
     berths
    0.40
     Plague
    0.40
    POSITIVE LOGITS
     pasando
    0.48
    size
    0.47
    url
    0.47
     güzel
    0.47
    RES
    0.46
    市内
    0.46
    ik
    0.45
    On
    0.45
    ol
    0.45
    OL
    0.45
    Act Density 0.004%

    No Known Activations