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

    Neuronpedia

    INDEX
    Explanations

    go file distributed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    source
    -0.71
     sources
    -0.69
    sources
    -0.67
    ímos
    -0.67
     Source
    -0.67
     source
    -0.67
     ź
    -0.66
     fuente
    -0.66
     Arbeit
    -0.65
     seats
    -0.65
    POSITIVE LOGITS
    ULAR
    0.83
     xxi
    0.73
    Види
    0.73
    ساس
    0.73
    SEB
    0.71
    Pea
    0.71
     Vesta
    0.69
     Larsson
    0.69
     seb
    0.67
     kz
    0.66
    Act Density 0.077%

    No Known Activations