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

    Neuronpedia

    INDEX
    Explanations

    identity theft and fraud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memberikan
    -0.09
     moderators
    -0.08
     perusahaan
    -0.08
     fold
    -0.08
     expressive
    -0.08
    )n
    -0.08
     folding
    -0.08
    τέρ
    -0.08
    utherland
    -0.08
     Arthur
    -0.08
    POSITIVE LOGITS
     Kang
    0.08
    했습니다
    0.08
    itha
    0.08
    igue
    0.08
    ipherals
    0.07
    하세요
    0.07
     银
    0.07
     నివ
    0.07
     예방
    0.07
    accine
    0.07
    Act Density 0.007%

    No Known Activations