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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ウス
    -0.07
    �
    -0.06
    CLK
    -0.06
    타
    -0.06
     caratter
    -0.06
    セット
    -0.06
    ンの
    -0.06
    џџџ
    -0.06
    merchant
    -0.06
    .Par
    -0.06
    POSITIVE LOGITS
    ,target
    0.07
     hysteria
    0.07
     sched
    0.07
    [email
    0.06
    (PHP
    0.06
    mpl
    0.06
     깨
    0.06
    容
    0.06
     openssl
    0.06
     blouse
    0.06
    Act Density 0.005%

    No Known Activations