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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology associated with defining concepts and linguistic nuances

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

    idiomatic expressions, words in quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.50
     Roskov
    -0.41
    AutoSize
    -0.39
    BagConstraints
    -0.38
     guestbook
    -0.37
    zeß
    -0.36
    exitRule
    -0.36
     biografias
    -0.36
     initComponents
    -0.35
    elevator
    -0.35
    POSITIVE LOGITS
    Tikang
    0.48
     sartén
    0.43
     manguera
    0.43
    ceğine
    0.42
    zbęd
    0.39
    Atentamente
    0.39
    chaleco
    0.38
     contextLoads
    0.38
     ✭✭
    0.38
     Blow
    0.37
    Act Density 0.052%

    No Known Activations