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

    Neuronpedia

    INDEX
    Explanations

    formatting lists and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    0.52
    ci
    0.50
    volume
    0.50
    ern
    0.48
     blockbuster
    0.47
     volumen
    0.47
     Volume
    0.46
     volume
    0.46
    iy
    0.46
    sell
    0.45
    POSITIVE LOGITS
     szy
    0.49
    Severity
    0.49
    Ú
    0.48
     робити
    0.47
    ಏ
    0.46
    Además
    0.45
    À
    0.45
    Ą
    0.45
    हा
    0.45
    หน้า
    0.44
    Act Density 0.004%

    No Known Activations