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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trees
    -0.07
    892
    -0.07
    436
    -0.07
    439
    -0.06
     Jennifer
    -0.06
    arios
    -0.06
     slots
    -0.06
    cb
    -0.06
     character
    -0.06
     Voice
    -0.06
    POSITIVE LOGITS
    اقل
    0.07
     فس
    0.07
     кін
    0.06
    ゴリ
    0.06
     ніж
    0.06
     Opcode
    0.06
     graceful
    0.06
    нг
    0.06
    );
↵
    0.06
     ділян
    0.06
    Act Density 0.007%

    No Known Activations