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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginnt
    0.82
     substantiate
    0.82
     kämp
    0.81
     подтвер
    0.79
     spies
    0.77
     políticos
    0.76
     которая
    0.76
     solace
    0.76
     Kauf
    0.75
     Butte
    0.75
    POSITIVE LOGITS
     ін
    0.85
    М
    0.84
    ה
    0.78
    ње
    0.77
    ב
    0.77
    クリスマス
    0.75
     сучас
    0.75
    で
    0.74
     різ
    0.73
    আ
    0.72
    Act Density 0.002%

    No Known Activations