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

    Neuronpedia

    INDEX
    Explanations

    daily grind social media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ری
    0.99
    ти
    0.95
    ла
    0.84
    ură
    0.84
    ל
    0.84
    тері
    0.83
    ulents
    0.77
    一丝
    0.77
    onant
    0.77
    দ্ম
    0.76
    POSITIVE LOGITS
     Каждый
    0.87
     erad
    0.87
    FILES
    0.86
     huts
    0.85
    für
    0.84
    Datei
    0.83
     autoload
    0.82
     Echt
    0.82
    害者
    0.80
     chini
    0.80
    Act Density 0.000%

    No Known Activations