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

    Neuronpedia

    INDEX
    Explanations

    list item indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }\}$.
    1.99
    else
    1.92
     supplemented
    1.91
    ]}.
    1.87
     autres
    1.87
     lainnya
    1.87
    윅
    1.85
    ients
    1.79
     evidence
    1.76
     other
    1.76
    POSITIVE LOGITS
    7
    1.17
    8
    1.12
    5
    1.06
    9
    0.97
    4
    0.95
    6
    0.89
    Need
    0.89
    1
    0.86
    Wearing
    0.78
     combust
    0.78
    Act Density 1.071%

    No Known Activations