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

    Neuronpedia

    INDEX
    Explanations

    Fukushima

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the Fukushima Daiichi nuclear power plant or the Fukushima nuclear disaster.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    adt
    -0.06
    ader
    -0.06
     Paolo
    -0.06
     Jarvis
    -0.06
     Buccane
    -0.06
    drop
    -0.06
     villagers
    -0.06
    AAC
    -0.06
     denim
    -0.06
    arrison
    -0.05
    POSITIVE LOGITS
     Fukushima
    0.08
     Flu
    0.08
    shima
    0.08
     assemblies
    0.07
     사실
    0.07
     phủ
    0.07
    нима
    0.07
    岛
    0.06
    кус
    0.06
    acists
    0.06
    Act Density 0.002%

    No Known Activations