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

    Neuronpedia

    INDEX
    Explanations

    argued then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     तरह
    0.86
    佾
    0.84
    asambhavam
    0.84
     vorm
    0.82
     devre
    0.82
    adham
    0.81
     मानकों
    0.81
     japan
    0.80
     выс
    0.80
    を含
    0.79
    POSITIVE LOGITS
    د
    0.89
     posture
    0.83
    it
    0.81
    at
    0.80
    ↵
    0.79
    m
    0.79
     години
    0.77
    id
    0.72
    ساز
    0.71
    িকা
    0.71
    Act Density 0.000%

    No Known Activations