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

    Neuronpedia

    INDEX
    Explanations

    gore and violence

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of body parts—especially in dismemberment or gore contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _path
    -0.07
     Wire
    -0.06
    "But
    -0.06
     ip
    -0.06
     splendid
    -0.06
    etsk
    -0.06
    톤
    -0.06
     Glen
    -0.06
     injection
    -0.06
    "And
    -0.06
    POSITIVE LOGITS
    .Float
    0.07
    .New
    0.06
    .notifications
    0.06
     rais
    0.06
    engin
    0.06
     Oregon
    0.06
    PDO
    0.06
    ї
    0.06
    OptionsResolver
    0.06
    otlin
    0.06
    Act Density 0.023%

    No Known Activations