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

    Neuronpedia

    INDEX
    Explanations

    News headlines Q&A

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kka
    -0.79
    Offset
    -0.78
    年以上
    -0.77
    spiritual
    -0.76
    anteen
    -0.75
     fidèles
    -0.73
    țiile
    -0.72
     Polskiego
    -0.71
     ablation
    -0.71
     Anlage
    -0.70
    POSITIVE LOGITS
     fb
    0.98
     FB
    0.91
    FB
    0.84
     güneş
    0.79
     LCD
    0.79
     panel
    0.77
    BLL
    0.73
    液晶
    0.72
    fb
    0.71
     Liqu
    0.70
    Act Density 0.008%

    No Known Activations