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

    Neuronpedia

    INDEX
    Explanations

    numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers, references, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.58
     المعيارى
    -0.57
    expandindo
    -0.57
     surla
    -0.57
     ſch
    -0.55
    ロウィン
    -0.55
     ſol
    -0.55
     faſt
    -0.53
    ihnachten
    -0.52
     indígen
    -0.51
    POSITIVE LOGITS
     türlü
    0.38
     pe
    0.38
     <<<<<<<<<<<<<<
    0.38
    line
    0.37
     line
    0.36
    pe
    0.35
    //
    0.35
     conectar
    0.34
    πη
    0.33
     team
    0.33
    Act Density 0.002%

    No Known Activations