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

    Neuronpedia

    INDEX
    Explanations

    academic terminology and structure in text

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

    sentence start keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.68
     contextLoads
    -0.68
    CodeAttribute
    -0.66
     мәкал
    -0.64
    ſelves
    -0.64
     queſta
    -0.63
     Anſ
    -0.62
    featureID
    -0.62
    Cyfarwyddwr
    -0.61
     diſt
    -0.61
    POSITIVE LOGITS
    awtextra
    0.36
     Gep
    0.35
     myself
    0.35
     para
    0.35
     Bryan
    0.33
     denk
    0.33
     Das
    0.32
    帖最后由
    0.32
    Gep
    0.31
     Myself
    0.31
    Act Density 0.099%

    No Known Activations