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

    Neuronpedia

    INDEX
    Explanations

    hypocrisy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CI
    -0.07
    (extension
    -0.07
     Orb
    -0.06
     explor
    -0.06
    结果
    -0.06
    �
    -0.06
    _SOL
    -0.06
     colabor
    -0.06
    VEST
    -0.05
     pourrait
    -0.05
    POSITIVE LOGITS
     hypocrisy
    0.11
     hypoc
    0.09
    مق
    0.07
     millions
    0.07
    ocrisy
    0.07
     INTERN
    0.07
     sanitize
    0.07
     düşünc
    0.06
    dol
    0.06
    اید
    0.06
    Act Density 0.001%

    No Known Activations