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

    Neuronpedia

    INDEX
    Explanations

    award

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    こちら
    -0.08
    에는
    -0.07
    횃
    -0.07
     harness
    -0.07
     execute
    -0.07
    人民银行
    -0.07
    来形容
    -0.07
    CRM
    -0.07
     الشمال
    -0.07
    谁能
    -0.07
    POSITIVE LOGITS
    مواف
    0.08
     такого
    0.07
     µ
    0.07
    𝐜
    0.07
    >())↵
    0.07
     psychedelic
    0.07
    .after
    0.07
     CALL
    0.06
    The
    0.06
     millenn
    0.06
    Act Density 0.012%

    No Known Activations