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

    Neuronpedia

    INDEX
    Explanations

    code, comments, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INA
    0.47
    Queens
    0.45
    Mountains
    0.44
    IRCON
    0.42
    CUSSION
    0.42
    隘
    0.41
    QUE
    0.41
    Colonne
    0.40
    ALTERNATIVE
    0.40
    STIT
    0.40
    POSITIVE LOGITS
     optimize
    0.45
     optimizes
    0.43
    optimize
    0.43
    经常
    0.42
     discourage
    0.42
     అలాగే
    0.41
     minimize
    0.41
     max
    0.40
     vogue
    0.40
     minimise
    0.40
    Act Density 0.071%

    No Known Activations