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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of violence, armed attacks, or security threats in political or conflict‐related news.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    pheres
    -0.07
     ν
    -0.07
    noc
    -0.06
    вався
    -0.06
     balance
    -0.06
    {name
    -0.06
    ;height
    -0.06
    牙
    -0.06
     Sting
    -0.06
     Kle
    -0.06
    POSITIVE LOGITS
     ослож
    0.06
    тобы
    0.06
     připom
    0.06
    恶
    0.06
    ्पर
    0.06
    ekte
    0.06
     tuổi
    0.06
    -chief
    0.06
    .TableLayoutPanel
    0.06
    .synthetic
    0.06
    Act Density 0.026%

    No Known Activations