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

    Neuronpedia

    INDEX
    Explanations

    circumstances and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astikan
    0.44
    TDto
    0.44
    categorias
    0.42
     partidas
    0.42
     NVARCHAR
    0.41
     लिए
    0.41
     pérdidas
    0.41
    ﹃
    0.41
    이가
    0.41
     müşteri
    0.41
    POSITIVE LOGITS
     Vermont
    0.44
     grandmother
    0.42
     Meadow
    0.42
     училище
    0.41
     Syracuse
    0.41
     retreat
    0.40
     Sussex
    0.40
     radical
    0.40
     Connecticut
    0.39
     stepping
    0.39
    Act Density 0.004%

    No Known Activations