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

    Neuronpedia

    INDEX
    Explanations

    credibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SYS
    -0.07
     LCD
    -0.07
     Tk
    -0.07
    _GRP
    -0.06
    \Schema
    -0.06
    fad
    -0.06
    -Star
    -0.06
    AAC
    -0.06
     Finger
    -0.06
     harassment
    -0.06
    POSITIVE LOGITS
    [action
    0.06
    -ranging
    0.06
     tại
    0.06
    /results
    0.06
    ewitness
    0.06
    ancements
    0.06
     리
    0.06
     війсь
    0.06
    �始化
    0.06
     }),↵↵
    0.06
    Act Density 0.003%

    No Known Activations