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

    Neuronpedia

    INDEX
    Explanations

    likelihood

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any token patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anguage
    -0.07
    ´s
    -0.07
    azzo
    -0.06
     sermon
    -0.06
    590
    -0.06
    р
    -0.06
     Тур
    -0.06
     Patron
    -0.06
     receptor
    -0.06
    ерта
    -0.06
    POSITIVE LOGITS
     likelihood
    0.11
    likelihood
    0.07
    elihood
    0.07
     Lik
    0.07
     Leaders
    0.07
    œ
    0.07
     lãi
    0.07
     MK
    0.06
    ":[
    0.06
     Lucas
    0.06
    Act Density 0.004%

    No Known Activations