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

    Neuronpedia

    INDEX
    Explanations

    technical jargon related to mathematics and programming concepts

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

    lambda calculus, formal systems, code assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    std
    -0.35
    йтинг
    -0.35
    andExpect
    -0.33
     std
    -0.28
     top
    -0.28
    àn
    -0.27
    timbangan
    -0.26
     Q
    -0.25
    findpost
    -0.25
     Top
    -0.24
    POSITIVE LOGITS
    rungsseite
    0.80
     surla
    0.71
    Vidite
    0.69
    tvguidetime
    0.69
     للاسماء
    0.68
     שוליים
    0.62
    AISSEE
    0.61
     kaarangay
    0.60
    ⟬
    0.59
     ſehr
    0.57
    Act Density 0.079%

    No Known Activations