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

    Neuronpedia

    INDEX
    Explanations

    si

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of experimental gene or protein knockdown via RNA interference (e.g. siRNA, knockdown, silencing).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .predict
    -0.07
    uis
    -0.06
     registrazione
    -0.06
    Зап
    -0.06
     Han
    -0.06
     perché
    -0.06
    aversal
    -0.06
     puedo
    -0.06
     embeddings
    -0.06
     Kam
    -0.06
    POSITIVE LOGITS
    _math
    0.08
    Who
    0.07
    .setEditable
    0.06
     APPLE
    0.06
        ↵↵
    0.06
    .faces
    0.06
    lou
    0.06
    terraform
    0.06
    ograf
    0.06
     ATTRIBUTE
    0.06
    Act Density 0.003%

    No Known Activations