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

    Neuronpedia

    INDEX
    Explanations

    conversational writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uu
    -0.07
    ,',
    -0.06
     Hi
    -0.06
    *u
    -0.06
    _AA
    -0.06
     ple
    -0.06
    ffe
    -0.06
     Ft
    -0.06
     Gig
    -0.06
    elial
    -0.06
    POSITIVE LOGITS
     Malaysia
    0.08
     української
    0.07
     استاند
    0.07
     ItemStack
    0.06
     bapt
    0.06
     mrb
    0.06
    	property
    0.06
     Bind
    0.06
    .drawString
    0.06
    iểm
    0.06
    Act Density 0.026%

    No Known Activations