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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equitable
    -0.07
    Fort
    -0.07
    езпеч
    -0.06
    Dimensions
    -0.06
     Representatives
    -0.06
    Graph
    -0.06
     brokerage
    -0.06
    violent
    -0.06
    гра
    -0.06
     Qt
    -0.06
    POSITIVE LOGITS
     annoy
    0.07
     jobject
    0.07
     },↵
    0.07
    <Integer
    0.06
     stuffing
    0.06
     hodiny
    0.06
     dříve
    0.06
    _inches
    0.06
     现
    0.06
    fine
    0.06
    Act Density 0.017%

    No Known Activations