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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and references to accessibility or availability

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

    condition or availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Orig
    -0.38
    Orig
    -0.35
    Kirche
    -0.35
    Hib
    -0.35
     Hib
    -0.34
     Wikiseite
    -0.34
     хи
    -0.34
     Bel
    -0.34
    StyleSheet
    -0.32
     zab
    -0.31
    POSITIVE LOGITS
     المعيارى
    0.53
     typelib
    0.53
    Personendaten
    0.53
     دیکھیے
    0.52
     nakalista
    0.51
    Kjelder
    0.49
     parachoque
    0.48
     cherchés
    0.48
    ftagPool
    0.48
    yntaxException
    0.48
    Act Density 0.088%

    No Known Activations