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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron is essentially “dead” and never activates for any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    وی
    -0.07
     дальней
    -0.06
    작
    -0.06
     timestamp
    -0.06
     Mos
    -0.06
     Lau
    -0.06
     astronomy
    -0.06
    生物
    -0.06
    	Port
    -0.06
    議
    -0.06
    POSITIVE LOGITS
     guardar
    0.07
    >-->↵
    0.07
    θεια
    0.06
     neod
    0.06
    avez
    0.06
    .slides
    0.06
                        ↵
    0.06
     Oct
    0.06
    .conn
    0.06
    ulf
    0.06
    Act Density 0.015%

    No Known Activations