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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and data handling

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

    exceeding limits or ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.63
     '\\;'
    -0.60
    帖最后由
    -0.56
     ModelRenderer
    -0.56
     dAtA
    -0.55
    +#+#
    -0.51
    rawDesc
    -0.50
    Tembelea
    -0.50
     allAfrica
    -0.49
    ImageContext
    -0.48
    POSITIVE LOGITS
     achieved
    0.47
     complied
    0.46
     Abweich
    0.44
     compliance
    0.42
     cumplimiento
    0.41
    KEYCODE
    0.40
     épaules
    0.39
     Achie
    0.39
     accomplished
    0.38
    Achie
    0.38
    Act Density 0.130%

    No Known Activations