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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lan
    -0.07
     troll
    -0.06
    prehensive
    -0.06
     ber
    -0.06
    quito
    -0.06
    nu
    -0.06
    _Line
    -0.06
    -vertical
    -0.06
     :'
    -0.06
     Deutschland
    -0.06
    POSITIVE LOGITS
    inh
    0.07
    	constructor
    0.06
     pronounce
    0.06
    bishop
    0.06
     heraus
    0.06
     expressing
    0.06
    onces
    0.06
     spouses
    0.06
     Geg
    0.06
    ostat
    0.06
    Act Density 0.006%

    No Known Activations