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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    0.61
    ཥ
    0.58
     ਦਵਾਈ
    0.57
    יל
    0.57
    Ꭸ
    0.55
    kében
    0.54
    фи
    0.54
    ני
    0.53
    ור
    0.53
    י
    0.52
    POSITIVE LOGITS
     This
    0.48
     H
    0.48
     D
    0.47
     A
    0.47
     Blockchain
    0.45
     Business
    0.45
     P
    0.44
     Architect
    0.44
     In
    0.43
     These
    0.43
    Act Density 0.190%

    No Known Activations