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

    Neuronpedia

    INDEX
    Explanations

    references to time and context-specific actions

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

    "beginning", "before", or "during"

    np_acts-logits-general · gemini-2.0-flash

    temporal sequencing before/during/after events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.43
     Référence
    -0.41
     deniz
    -0.38
     cow
    -0.37
     PartialEq
    -0.37
    endrait
    -0.37
    oneofs
    -0.36
    ław
    -0.36
    orld
    -0.35
    IBOutlet
    -0.35
    POSITIVE LOGITS
    日閲覧
    0.54
     Permite
    0.47
     signes
    0.45
    keyColumn
    0.45
     Meksiku
    0.44
     circonstances
    0.43
     useCallback
    0.42
     момент
    0.41
     незавершена
    0.41
     செய
    0.41
    Act Density 0.520%

    No Known Activations