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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dic
    -0.06
    новид
    -0.06
    DIG
    -0.06
    middle
    -0.05
    _DSP
    -0.05
     rising
    -0.05
     Swamp
    -0.05
     Hol
    -0.05
    iê
    -0.05
     risking
    -0.05
    POSITIVE LOGITS
     ак
    0.08
    355
    0.08
     Chevrolet
    0.07
     Harlem
    0.07
     thickness
    0.07
     кон
    0.07
     chic
    0.07
     фот
    0.07
     Stamford
    0.07
    jsc
    0.07
    Act Density 0.000%

    No Known Activations