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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宛
    -0.07
     luckily
    -0.06
     bezpieczeńst
    -0.06
     ту
    -0.06
    蘇
    -0.06
    Saudi
    -0.06
     flyer
    -0.06
    /flutter
    -0.06
     Font
    -0.06
    我还
    -0.06
    POSITIVE LOGITS
    헸
    0.08
    erson
    0.07
    _INS
    0.07
    虮
    0.07
    途径
    0.06
     herr
    0.06
    Ⓓ
    0.06
     Rifle
    0.06
    _pwm
    0.06
     vector
    0.06
    Act Density 0.103%

    No Known Activations