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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens appearing in import statements (i.e. class‐path/module import declarations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    nal
    -0.07
     novice
    -0.06
    .Interval
    -0.06
     BaseModel
    -0.06
    Santa
    -0.06
     tủ
    -0.06
    /utils
    -0.06
     Battery
    -0.06
    yslu
    -0.06
     MEDIA
    -0.06
    POSITIVE LOGITS
    .constructor
    0.07
    .book
    0.06
    argas
    0.06
    อบ
    0.06
    	display
    0.06
     emailAddress
    0.06
     Medic
    0.06
    buttonShape
    0.06
    Advertisements
    0.06
     disproportionately
    0.06
    Act Density 0.031%

    No Known Activations