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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MessageBox
    -0.08
     fire
    -0.07
     rout
    -0.07
     Sexo
    -0.06
    _cmds
    -0.06
    tim
    -0.06
     landfill
    -0.06
    -Mart
    -0.06
    ='')
    -0.06
    .format
    -0.06
    POSITIVE LOGITS
    роб
    0.07
     _,
    0.07
     Пра
    0.06
    	ss
    0.06
    PPER
    0.06
    OLUTION
    0.06
     disputed
    0.06
    خوان
    0.06
    ALLEL
    0.06
    rawer
    0.06
    Act Density 0.018%

    No Known Activations