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

    Neuronpedia

    INDEX
    Explanations

    IBM Power Architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ttest
    0.40
    స్తున్న
    0.38
    brochen
    0.38
     ['(?
    0.37
    क्ल
    0.35
    ह्
    0.35
    ceptible
    0.35
    𝐄
    0.34
     पहचान
    0.34
     টে
    0.33
    POSITIVE LOGITS
     NY
    0.55
    NY
    0.52
     NYC
    0.49
    纽约
    0.44
     food
    0.42
     nyc
    0.40
     sarebbe
    0.40
     Knicks
    0.40
     Adirond
    0.40
     chapter
    0.39
    Act Density 0.002%

    No Known Activations