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

    Neuronpedia

    INDEX
    Explanations

    contrasting limitations and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ・
    0.98
     Wish
    0.98
     -
    0.91
     ```
    0.90
     •
    0.90
     ●
    0.87
    Wish
    0.84
    0.84
     –
    0.83
    0.82
    POSITIVE LOGITS
    $"
    0.77
     estre
    0.77
    '$\
    0.77
    )：
    0.76
    ')$
    0.74
    💑
    0.74
    😧
    0.73
     рэгістра
    0.73
    ！)
    0.72
    😲
    0.71
    Act Density 0.032%

    No Known Activations