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

    Neuronpedia

    INDEX
    Explanations

    measures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     відповідаль
    -0.07
    _uv
    -0.06
     maint
    -0.06
     +**************
    -0.06
     Siri
    -0.06
    สะดวก
    -0.06
     nameof
    -0.06
    술
    -0.06
     openly
    -0.06
     관한
    -0.06
    POSITIVE LOGITS
     measures
    0.11
    attles
    0.07
     legal
    0.07
    اب
    0.07
    analysis
    0.07
    ''↵
    0.07
    valuation
    0.06
     critique
    0.06
     {{
    0.06
     Measures
    0.06
    Act Density 0.015%

    No Known Activations