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

    Neuronpedia

    INDEX
    Explanations

    numbers and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Punk
    0.42
    이지만
    0.40
    న్
    0.40
    ISING
    0.38
    },
    0.38
    ड़
    0.38
    Tw
    0.38
    ↵↵
    0.38
    ᱴ
    0.37
    डक
    0.37
    POSITIVE LOGITS
     ingat
    0.50
     dieses
    0.49
    leri
    0.48
     înt
    0.47
     meist
    0.47
     sü
    0.47
    کات
    0.46
    culus
    0.46
     reméd
    0.46
    لاش
    0.45
    Act Density 0.138%

    No Known Activations