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

    Neuronpedia

    INDEX
    Explanations

    notes on style or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    낫
    0.68
     অস্থ
    0.68
     ออนไลน์
    0.67
    PhysRev
    0.66
     pré
    0.65
    pren
    0.64
    તાવ
    0.64
    ismas
    0.61
     prema
    0.61
    瞧
    0.61
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.82
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.78
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.76
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.76
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.74
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.72
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.72
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.71
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.70
    Act Density 0.147%

    No Known Activations