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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sembl
    -0.07
    меч
    -0.07
    Sr
    -0.06
    =row
    -0.06
    ikh
    -0.06
    ikhail
    -0.06
     gbc
    -0.06
     sobě
    -0.06
    _Save
    -0.06
     Rune
    -0.06
    POSITIVE LOGITS
    CONDITION
    0.07
    "context
    0.07
    	select
    0.07
    ：↵
    0.07
    彩
    0.06
    	options
    0.06
    prises
    0.06
     invalidated
    0.06
    lod
    0.06
    еного
    0.06
    Act Density 0.001%

    No Known Activations