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

    Neuronpedia

    INDEX
    Explanations

    line breaks and wrapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    રી
    0.45
    resham
    0.43
    aurant
    0.42
    stoffe
    0.41
    president
    0.40
    oretto
    0.39
    ेंच
    0.39
    ništ
    0.38
    concent
    0.38
    គ
    0.38
    POSITIVE LOGITS
     breaks
    0.99
    breaks
    0.98
     break
    0.93
     Breaks
    0.90
     Break
    0.89
     breaking
    0.86
    Break
    0.83
    Breaking
    0.81
     Breaking
    0.78
    break
    0.77
    Act Density 0.020%

    No Known Activations