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

    Neuronpedia

    INDEX
    Explanations

    Please

    np_max-act · gemini-2.0-flash

    This neuron activates on the polite “please feel free to ask” invitation phrase.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ctor
    -0.07
     Tec
    -0.06
     بلند
    -0.06
     يك
    -0.06
    _firestore
    -0.06
     Mehr
    -0.06
    MHz
    -0.06
    Τα
    -0.06
    lomou
    -0.06
    말
    -0.06
    POSITIVE LOGITS
    Asian
    0.08
     McG
    0.07
    -radius
    0.07
     cardiovascular
    0.07
     certify
    0.07
    Course
    0.06
    _frames
    0.06
    eland
    0.06
    zer
    0.06
     moms
    0.06
    Act Density 0.015%

    No Known Activations