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

    Neuronpedia

    INDEX
    Explanations

    instances of significantly long or complex programming structure or code blocks

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

    code library usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aveug
    -0.46
    cluye
    -0.44
     Spuren
    -0.41
     wzgl
    -0.40
     Veuillez
    -0.40
     Connectez
    -0.40
    OGND
    -0.40
     lectores
    -0.38
     szkol
    -0.38
     Empfindung
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.58
     NIS
    0.48
    CommandText
    0.45
     CanadaChoose
    0.45
    RemoveField
    0.44
    出版年
    0.43
     kaynağından
    0.43
     Administrativna
    0.43
     NIV
    0.42
     PDB
    0.42
    Act Density 0.034%

    No Known Activations