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

    Neuronpedia

    INDEX
    Explanations

    use to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.81
    elle
    0.79
     musicale
    0.77
    ่
    0.75
    اء
    0.75
     मंड
    0.74
    treatment
    0.73
    ์
    0.72
    ജന
    0.71
    pc
    0.71
    POSITIVE LOGITS
    ೇತ್ರ
    0.95
     chromatographed
    0.92
    Tracks
    0.91
    ו
    0.89
     guna
    0.88
     Astral
    0.87
     lumen
    0.86
    ными
    0.85
    Β
    0.84
     hijack
    0.84
    Act Density 0.002%

    No Known Activations