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

    Neuronpedia

    INDEX
    Explanations

    existence

    np_max-act · gemini-2.0-flash

    The neuron is triggered by mentions of being alive or living (e.g. “live,” “alive,” “life”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Genius
    -0.07
    ових
    -0.07
    .Place
    -0.06
    -Type
    -0.06
    一样
    -0.06
    ，你
    -0.06
    Rates
    -0.06
    zero
    -0.06
     folded
    -0.06
     YYSTACK
    -0.06
    POSITIVE LOGITS
     Maced
    0.07
    mad
    0.07
    comes
    0.07
    Unable
    0.06
     survives
    0.06
     survived
    0.06
     Honduras
    0.06
     Sadly
    0.06
    errated
    0.06
     survive
    0.06
    Act Density 0.134%

    No Known Activations