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

    Neuronpedia

    INDEX
    Explanations

    references to time-related phrases, particularly those indicating recent events

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

    "Last" followed by time-related words

    np_acts-logits-general · gemini-2.0-flash

    last followed by time indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.61
    \{\\
    -0.59
     defaultstate
    -0.59
     splet
    -0.58
     pozdě
    -0.58
    PyExc
    -0.58
    TintMode
    -0.58
    VideoCapture
    -0.56
     vė
    -0.55
    IsMutable
    -0.55
    POSITIVE LOGITS
     resort
    0.97
     minute
    0.95
    minute
    0.93
    est
    0.83
    resort
    0.83
    ingly
    0.82
     Resort
    0.81
    Resort
    0.80
    ditch
    0.78
     straw
    0.77
    Act Density 0.065%

    No Known Activations