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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    f
    -0.06
    ITU
    -0.06
    Increasing
    -0.06
    $obj
    -0.06
     ifade
    -0.06
    /general
    -0.06
    一般
    -0.06
    стати
    -0.06
    ニニ
    -0.06
    categorie
    -0.06
    POSITIVE LOGITS
    _SAFE
    0.07
     cheapest
    0.07
    acağı
    0.06
    .k
    0.06
    .Mouse
    0.06
    -local
    0.06
     文
    0.06
     reb
    0.06
    .ar
    0.06
    -'
    0.06
    Act Density 0.003%

    No Known Activations