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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and transitions between concepts

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

    prepositions and linkages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.75
    OGND
    -0.67
    )"),
    -0.66
    AccessorTable
    -0.65
    ੝
    -0.63
    fjspx
    -0.60
    brtc
    -0.60
    RegistryLite
    -0.59
     Efq
    -0.59
     @"/
    -0.57
    POSITIVE LOGITS
     chiaramente
    0.32
     BEN
    0.30
     convocatoria
    0.30
     metrów
    0.29
     itself
    0.28
     mwan
    0.28
     inauguración
    0.27
     contemporain
    0.27
     these
    0.27
    tering
    0.27
    Act Density 0.309%

    No Known Activations