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

    Neuronpedia

    INDEX
    Explanations

    echo

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptions of a shadowy void or swirling darkness—phrases evoking a spinning, chaotic nothingness.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    struk
    -0.07
    .routes
    -0.07
     Το
    -0.06
     Plain
    -0.06
     Management
    -0.06
    “But
    -0.06
     wizard
    -0.06
    getc
    -0.06
    'ın
    -0.06
     tả
    -0.06
    POSITIVE LOGITS
     echoes
    0.08
     echoing
    0.08
     memorable
    0.08
     echoed
    0.08
    响
    0.07
     відбу
    0.07
    Anchor
    0.07
     poignant
    0.06
     overlapping
    0.06
     resonate
    0.06
    Act Density 0.004%

    No Known Activations