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

    Neuronpedia

    INDEX
    Explanations

    negative signs or indicators in code

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

    filename orhttphttps references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ChromeDriver
    -0.45
     illustrationer
    -0.45
    WithMany
    -0.44
    şört
    -0.44
     turística
    -0.44
     Italij
    -0.43
     لينك
    -0.42
     spesa
    -0.42
     alimentaria
    -0.41
     pouvoit
    -0.41
    POSITIVE LOGITS
    expandindo
    0.71
     filename
    0.70
     виправивши
    0.69
    uxxxx
    0.64
     مشين
    0.60
     Мексичка
    0.58
    httphttps
    0.57
    Filename
    0.55
    filename
    0.55
     nahilalakip
    0.54
    Act Density 0.001%

    No Known Activations