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

    Neuronpedia

    INDEX
    Explanations

    categorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Voc
    -0.07
    ㅆ
    -0.07
    doch
    -0.06
     década
    -0.06
    	elif
    -0.06
    ӡ
    -0.06
    旞
    -0.06
     ejac
    -0.06
    .jet
    -0.06
    𫘨
    -0.06
    POSITIVE LOGITS
    (up
    0.08
     dollars
    0.08
    .footer
    0.08
    _details
    0.07
     Dudley
    0.07
    _fee
    0.07
    -Russian
    0.07
    👟
    0.07
    SHIFT
    0.07
    (enable
    0.07
    Act Density 0.032%

    No Known Activations