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

    Neuronpedia

    INDEX
    Explanations

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     temptation
    1.00
     wrist
    0.97
     vor
    0.95
    াত্মক
    0.94
    ચ
    0.92
     war
    0.92
     pencils
    0.91
    ोट
    0.90
     rods
    0.88
     pencil
    0.87
    POSITIVE LOGITS
    aking
    1.03
    ridge
    0.91
    cip
    0.87
    cular
    0.81
    लपुर
    0.78
    idd
    0.78
     integrante
    0.78
    cipe
    0.77
    রিদ্র
    0.74
    ners
    0.73
    Act Density 0.152%

    No Known Activations