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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    netje
    0.93
    ément
    0.89
    theless
    0.86
    ită
    0.83
    ępnie
    0.83
    oğlu
    0.83
    sset
    0.83
    dì
    0.83
    oncé
    0.82
    ándole
    0.81
    POSITIVE LOGITS
    ↵
    1.20
    ↵↵↵
    1.03
    .
    0.95
    "/>
    0.92
    -(
    0.90
    """
    0.89
    -.
    0.84
    -)
    0.83
    .</
    0.82
    <'
    0.81
    Act Density 0.000%

    No Known Activations