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

    Neuronpedia

    INDEX
    Explanations

    non-English, technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vn
    -0.07
     arranging
    -0.06
    klä
    -0.06
    BackgroundColor
    -0.06
    ést
    -0.06
     impeccable
    -0.06
    роз
    -0.06
    mv
    -0.06
    gado
    -0.06
    む
    -0.06
    POSITIVE LOGITS
    .game
    0.07
     routines
    0.06
    CONF
    0.06
     tasks
    0.06
     bios
    0.06
     mundane
    0.06
     smells
    0.06
     compensated
    0.06
    事務
    0.06
    核
    0.06
    Act Density 0.054%

    No Known Activations