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

    Neuronpedia

    INDEX
    Explanations

    These

    np_max-act · gemini-2.0-flash

    The neuron detects phrases that introduce summary or conclusion statements (e.g. “These results,” “This signaling,” “These findings”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     traceback
    -0.06
    imitives
    -0.06
    lettes
    -0.06
    Reusable
    -0.06
    toupper
    -0.06
     Readonly
    -0.06
    .relative
    -0.06
    .NotNull
    -0.06
    baz
    -0.06
    Stories
    -0.06
    POSITIVE LOGITS
     demol
    0.07
     spacious
    0.07
    (users
    0.07
    _US
    0.06
     мер
    0.06
    ％
    0.06
    -exec
    0.06
    (TIM
    0.06
     удов
    0.06
    "os
    0.06
    Act Density 0.029%

    No Known Activations