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

    Neuronpedia

    INDEX
    Explanations

    puppet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WATCH
    -0.07
    liter
    -0.07
    withdraw
    -0.06
    setVisibility
    -0.06
    jack
    -0.06
     DOM
    -0.06
     chew
    -0.06
     gra
    -0.06
     Leeds
    -0.06
     Peak
    -0.06
    POSITIVE LOGITS
    	EXPECT
    0.07
    ################################
    0.07
     Это
    0.07
     капіт
    0.06
    ümü
    0.06
     Aralık
    0.06
     питань
    0.06
     (_,
    0.06
    (resultado
    0.06
    �u
    0.06
    Act Density 0.003%

    No Known Activations