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

    Neuronpedia

    INDEX
    Explanations

    change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cout
    1.56
    ким
    1.55
    dl
    1.52
    }$=
    1.50
    곧
    1.48
    vrez
    1.47
    খ
    1.45
     versch
    1.45
     разрабо
    1.44
    }$(
    1.44
    POSITIVE LOGITS
     చెందిన
    1.99
     사항
    1.88
    లు
    1.84
    әт
    1.82
    ist
    1.80
    NSDictionary
    1.79
     wrought
    1.77
    нула
    1.73
    їв
    1.72
    사항
    1.70
    Act Density 0.020%

    No Known Activations