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

    Neuronpedia

    INDEX
    Explanations

    /types

    np_max-act · gemini-2.0-flash

    The neuron is keyed to Go client‐library subpackage identifiers (e.g. “types” and “watch”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Moral
    -0.07
    (V
    -0.06
     fuzzy
    -0.06
     moral
    -0.06
     destroyer
    -0.06
    inn
    -0.06
     Montreal
    -0.05
     CV
    -0.05
    環
    -0.05
    cca
    -0.05
    POSITIVE LOGITS
     рес
    0.07
    .Symbol
    0.07
    phil
    0.07
    Difference
    0.07
    TypeID
    0.07
     іншими
    0.06
    에는
    0.06
     Publishers
    0.06
    borough
    0.06
    ThanOr
    0.06
    Act Density 0.001%

    No Known Activations