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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey varying levels of understanding or interpretation of concepts

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

    handling and approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    moveToFirst
    -0.44
     vectorielle
    -0.34
     ocor
    -0.34
     sauve
    -0.33
    ErrUnexpectedEOF
    -0.33
     hvě
    -0.32
     pareil
    -0.31
    addContainerGap
    -0.31
     cæ
    -0.31
     platí
    -0.31
    POSITIVE LOGITS
     misuse
    0.56
     misused
    0.56
    IndentedString
    0.55
     approach
    0.55
    parsedMessage
    0.54
     Umgang
    0.52
    approach
    0.51
     NSCoder
    0.51
    QMetaType
    0.49
     approche
    0.47
    Act Density 0.185%

    No Known Activations