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

    Neuronpedia

    INDEX
    Explanations

    method and optical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skill
    0.98
     skilled
    0.93
     skills
    0.85
    skilled
    0.84
     special
    0.83
    ordinary
    0.82
     clinician
    0.82
     Skill
    0.76
     ordinary
    0.76
     notable
    0.74
    POSITIVE LOGITS
    ὼ
    0.75
     секу
    0.73
    eral
    0.72
     русских
    0.71
     Ember
    0.70
    テリア
    0.70
    plicate
    0.68
     GIF
    0.68
    िफ्ट
    0.68
    тивних
    0.66
    Act Density 0.026%

    No Known Activations