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

    Neuronpedia

    INDEX
    Explanations

    priority rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ere
    0.81
    lari
    0.79
     Sélection
    0.79
     Enf
    0.77
     Під
    0.77
    handlungen
    0.77
     mlijeka
    0.75
    helix
    0.74
    ركة
    0.73
    rologist
    0.73
    POSITIVE LOGITS
    一种
    0.73
    endum
    0.70
    бна
    0.69
     comedian
    0.66
    AN
    0.65
    森
    0.65
     soul
    0.63
     shoe
    0.62
    ({})
    0.62
    间
    0.62
    Act Density 0.000%

    No Known Activations