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

    Neuronpedia

    INDEX
    Explanations

    words indicating conditions or states of being related to actions or existence

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

    what if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.43
    最快更新
    -0.39
    Atsauces
    -0.36
    sendRedirect
    -0.36
     please
    -0.34
     förr
    -0.34
    htbp
    -0.33
    település
    -0.33
    ORPG
    -0.32
     önce
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.76
     للمعارف
    0.58
    帖最后由
    0.57
     Offisielt
    0.51
    sofá
    0.50
     Numerade
    0.49
    NewUrlParser
    0.47
    EndContext
    0.47
    الحياه
    0.46
     finalised
    0.46
    Act Density 0.033%

    No Known Activations