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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    portlet
    -0.07
    oğunluk
    -0.07
    に関
    -0.07
     Bru
    -0.06
     apis
    -0.06
    -prof
    -0.06
     magna
    -0.06
     ل
    -0.06
    >Data
    -0.06
    _Release
    -0.06
    POSITIVE LOGITS
     GM
    0.07
    Own
    0.07
     adapters
    0.06
    396
    0.06
     dotted
    0.06
    getString
    0.06
     searchable
    0.06
    ()){↵
    0.06
     corners
    0.06
    	handler
    0.06
    Act Density 0.022%

    No Known Activations