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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sc
    -0.06
    wor
    -0.06
     seins
    -0.06
    Anne
    -0.06
    لمان
    -0.06
    Warehouse
    -0.06
    по
    -0.06
     qualidade
    -0.06
    safe
    -0.06
    los
    -0.06
    POSITIVE LOGITS
    -about
    0.07
    gebn
    0.07
     listop
    0.07
     "))↵
    0.06
    .dispatcher
    0.06
    polator
    0.06
    _WIFI
    0.06
    _DROP
    0.06
     GRA
    0.06
     příro
    0.06
    Act Density 0.027%

    No Known Activations