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

    Neuronpedia

    INDEX
    Explanations

    ist

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “transistor” (including its subword parts) in semiconductor technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    lsru
    -0.07
    _district
    -0.07
     Paz
    -0.07
     Tep
    -0.07
     conducive
    -0.06
     Pepper
    -0.06
     DateFormatter
    -0.06
    んです
    -0.06
     nearer
    -0.06
     NIGHT
    -0.06
    POSITIVE LOGITS
    .text
    0.07
    .security
    0.07
    omed
    0.07
    -channel
    0.06
     confines
    0.06
    .events
    0.06
     dope
    0.06
     depressed
    0.06
    Jane
    0.06
     Interviews
    0.06
    Act Density 0.004%

    No Known Activations