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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    movie
    -0.07
     gefunden
    -0.07
     Mines
    -0.07
    alignment
    -0.07
     condem
    -0.06
     Tournament
    -0.06
     identifiers
    -0.06
     species
    -0.06
    	parser
    -0.06
     راه
    -0.06
    POSITIVE LOGITS
     Implicit
    0.06
    公共
    0.06
    опис
    0.06
    čet
    0.06
     neler
    0.06
    addGroup
    0.06
     ün
    0.06
    lama
    0.06
     collective
    0.06
    zet
    0.06
    Act Density 0.357%

    No Known Activations