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

    Neuronpedia

    INDEX
    Explanations

    something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oved
    -0.08
    (it
    -0.06
    adients
    -0.06
     elephant
    -0.06
    око
    -0.06
     موج
    -0.06
    ход
    -0.06
    ществ
    -0.06
     property
    -0.06
     fresh
    -0.06
    POSITIVE LOGITS
    /ca
    0.07
     Закону
    0.07
     sect
    0.07
     diluted
    0.07
    _STR
    0.06
     اين
    0.06
     Exhibition
    0.06
    シア
    0.06
     الجن
    0.06
    .undo
    0.06
    Act Density 0.004%

    No Known Activations