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

    Neuronpedia

    INDEX
    Explanations

    Sudden events and transitions

    np_max-act · gemini-2.0-flash

    This neuron detects narrative transition markers—words that signal temporal or sequential shifts (e.g. “next,” “then,” “after,” “abruptly,” “time”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Apprentice
    -0.06
    ोस
    -0.06
    *",
    -0.06
    proper
    -0.06
     Rain
    -0.06
     öğret
    -0.06
    .Face
    -0.06
     rules
    -0.06
     suspense
    -0.06
     Giấy
    -0.06
    POSITIVE LOGITS
    pha
    0.06
    Enc
    0.06
    kov
    0.06
     HeaderComponent
    0.06
     들어
    0.06
    εξ
    0.06
    andise
    0.06
    Cong
    0.06
    нию
    0.06
    LEGRO
    0.06
    Act Density 0.099%

    No Known Activations