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

    Neuronpedia

    INDEX
    Explanations

    whistleblower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transcription
    -0.07
     bread
    -0.07
    lt
    -0.07
     :-↵
    -0.06
    pwd
    -0.06
     pris
    -0.06
    sector
    -0.06
     nie
    -0.06
     breastfeeding
    -0.06
     Gus
    -0.06
    POSITIVE LOGITS
     ölçü
    0.07
     whistleblower
    0.06
    えない
    0.06
     첨부파일
    0.06
     vyk
    0.06
    เคร
    0.06
    种
    0.06
     розрах
    0.06
    ICC
    0.06
    灭
    0.06
    Act Density 0.004%

    No Known Activations