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

    Neuronpedia

    INDEX
    Explanations

    URLs and web addresses

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

    URLs and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.58
    AISSEE
    -0.47
    TagMode
    -0.43
     tartalomajánló
    -0.43
    Personendaten
    -0.43
    évaluateur
    -0.42
    tvguidetime
    -0.42
    󠁢
    -0.42
    RegressionTest
    -0.41
    تقاوى
    -0.40
    POSITIVE LOGITS
    InvalidProtocol
    0.54
     EconPapers
    0.52
     raiſ
    0.48
    DoubleQuotes
    0.46
     autorytatywna
    0.44
    QSize
    0.41
     صوتيه
    0.40
    CppCodeGen
    0.40
    sendFile
    0.40
     становника
    0.40
    Act Density 0.005%

    No Known Activations