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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    曈
    -0.07
    公交车
    -0.07
     Mormon
    -0.07
     AFC
    -0.07
    -final
    -0.07
    읅
    -0.07
     jb
    -0.07
     tentative
    -0.06
     sore
    -0.06
    粗
    -0.06
    POSITIVE LOGITS
    LinkedIn
    0.08
    Θ
    0.07
    _arguments
    0.07
    created
    0.07
    (statement
    0.07
    })();↵
    0.07
     randomness
    0.07
    monthly
    0.06
    _chance
    0.06
    decrypt
    0.06
    Act Density 0.000%

    No Known Activations