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

    Neuronpedia

    INDEX
    Explanations

    override keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     растение
    0.44
     ஏனெ
    0.44
     হাও
    0.42
     lembut
    0.42
     konfer
    0.42
     इंफॉर्मेशन
    0.41
     egyszerű
    0.41
     изменения
    0.41
     ezzel
    0.41
     अनुसार
    0.41
    POSITIVE LOGITS
    როს
    0.45
    after
    0.40
    s
    0.39
    viewDidLoad
    0.39
    appreciated
    0.38
    診
    0.38
     Какие
    0.36
    displayed
    0.36
     父
    0.36
    راحی
    0.35
    Act Density 0.005%

    No Known Activations