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

    Neuronpedia

    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash

    This neuron detects interface or navigation action words and labels (e.g. Search, Play, Export, Subscribe, Video).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Bro
    -0.07
    apk
    -0.07
    IMP
    -0.07
    mnop
    -0.07
    gn
    -0.06
     Mat
    -0.06
     mining
    -0.06
    -google
    -0.06
     ramps
    -0.06
    uments
    -0.06
    POSITIVE LOGITS
     cautiously
    0.06
     confined
    0.06
     fle
    0.06
    apeutic
    0.06
     humili
    0.06
    aptured
    0.06
    χη
    0.06
    .Quantity
    0.06
    credible
    0.05
     второй
    0.05
    Act Density 0.025%

    No Known Activations