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

    Neuronpedia

    INDEX
    Explanations

    Hallmark movie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Liter
    0.50
    ż
    0.50
    し
    0.50
    R
    0.49
    ре
    0.49
    Cabinet
    0.49
    Repair
    0.48
    Wine
    0.47
    Be
    0.46
    Arabic
    0.46
    POSITIVE LOGITS
     प्रक्रियाओं
    0.51
    の名
    0.50
    गणना
    0.49
    ध्यक्ष
    0.49
     тести
    0.49
    Aslamualaikum
    0.49
     configurable
    0.49
     dotycz
    0.49
    денциа
    0.49
     ступен
    0.48
    Act Density 0.000%

    No Known Activations