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

    Neuronpedia

    INDEX
    Explanations

    problems and challenges

    np_max-act · gemini-2.0-flash

    The neuron detects story‐telling or plot‐progression terms—words that signal unfolding events, challenges, or ensuing action in a synopsis.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bent
    -0.08
     refuge
    -0.07
     sue
    -0.07
     charged
    -0.07
     chest
    -0.07
    Inspect
    -0.07
     Baptist
    -0.07
    .but
    -0.06
     Lent
    -0.06
    icks
    -0.06
    POSITIVE LOGITS
     EDUC
    0.06
     irq
    0.06
     Speak
    0.06
    "name
    0.06
    plitude
    0.06
    đ
    0.06
    Đ
    0.06
    цієн
    0.06
    ference
    0.05
    matchCondition
    0.05
    Act Density 0.045%

    No Known Activations