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

    Neuronpedia

    INDEX
    Explanations

    search queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deste
    -0.06
     então
    -0.06
     uży
    -0.06
     rozdíl
    -0.06
    ζί
    -0.06
     αφ
    -0.06
    ス
    -0.06
     Fritz
    -0.06
     campos
    -0.06
     Obviously
    -0.06
    POSITIVE LOGITS
    How
    0.07
    gii
    0.06
    _tok
    0.06
    $data
    0.06
    _;
↵
    0.06
    Which
    0.06
     dex
    0.06
    }

↵
    0.06
     pdo
    0.06
    coc
    0.06
    Act Density 0.003%

    No Known Activations