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

    Neuronpedia

    INDEX
    Explanations

    timestamps or time-related information in a document

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

    time, numbers, user turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtand
    -0.70
    RenderAtEndOf
    -0.69
     للمعارف
    -0.65
     queſta
    -0.65
    Abit
    -0.65
     surla
    -0.64
    tagHelperRunner
    -0.64
    BufferException
    -0.63
     ſche
    -0.63
    ########.
    -0.63
    POSITIVE LOGITS
    ed
    0.41
     afternoon
    0.36
     <<
    0.32
    «
    0.31
     midnight
    0.31
    ###
    0.31
     South
    0.31
    schod
    0.30
        
    0.30
    oacute
    0.30
    Act Density 0.010%

    No Known Activations