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

    Neuronpedia

    INDEX
    Explanations

    specific error types and expressions of importance or significant outcomes

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

    multilingual code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    errHandler
    -0.55
     africains
    -0.48
    empuan
    -0.47
     human
    -0.44
     Hart
    -0.44
     möjlighet
    -0.44
     mauvaise
    -0.43
     hemsida
    -0.43
     gomma
    -0.43
    mantec
    -0.43
    POSITIVE LOGITS
     sẽ
    1.27
    Autoritní
    0.79
     ſind
    0.68
    omiast
    0.62
     contextLoads
    0.58
     ſhall
    0.56
     CreateTagHelper
    0.54
    จึง
    0.53
     nếu
    0.52
     จะ
    0.52
    Act Density 0.001%

    No Known Activations