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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.76
    ized
    0.61
     \
    0.55
    arly
    0.50
    öffentlich
    0.48
     Saturday
    0.48
    uted
    0.48
    iciais
    0.46
    hips
    0.46
     최대한
    0.46
    POSITIVE LOGITS
    の
    0.96
    在
    0.86
    ز
    0.86
    的
    0.84
     in
    0.82
     في
    0.82
    त
    0.81
    의
    0.81
    ر
    0.81
    ين
    0.75
    Act Density 0.104%

    No Known Activations