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

    Neuronpedia

    INDEX
    Explanations

    appropriate/relevant

    np_max-act · gemini-2.0-flash

    This neuron primarily recognizes instances of the word “appropriate.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     RSA
    -0.07
    -tests
    -0.07
     Faculty
    -0.06
    _four
    -0.06
    遊
    -0.06
     Indoor
    -0.06
     list
    -0.06
    ethe
    -0.06
     directors
    -0.06
    .multiply
    -0.06
    POSITIVE LOGITS
     disillusion
    0.07
     devastating
    0.07
    alem
    0.07
     intimidating
    0.06
     tears
    0.06
     otp
    0.06
    .scrollView
    0.06
     بم
    0.06
    sockopt
    0.06
     druhou
    0.06
    Act Density 0.022%

    No Known Activations