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

    Neuronpedia

    INDEX
    Explanations

    Numerical comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Constraints
    -0.08
    Choices
    -0.08
    Teach
    -0.08
    Consent
    -0.07
    208
    -0.07
    Translator
    -0.07
    Economic
    -0.07
    Threads
    -0.07
    _COLUMNS
    -0.07
     constraints
    -0.07
    POSITIVE LOGITS
    順位
    0.09
     positioned
    0.09
     क्रम
    0.09
     incomparable
    0.08
     positi
    0.08
     Comparable
    0.08
    _ring
    0.08
     סדר
    0.08
    凌
    0.08
     überlegen
    0.08
    Act Density 0.029%

    No Known Activations