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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drv
    -0.06
    vä
    -0.06
    そんな
    -0.06
     hvordan
    -0.06
     sàn
    -0.06
    bookmark
    -0.06
    ghan
    -0.06
    하자
    -0.06
     다른
    -0.06
    	IN
    -0.06
    POSITIVE LOGITS
     launch
    0.08
     launched
    0.07
     tipo
    0.06
    amples
    0.06
     sounded
    0.06
    lerdi
    0.06
    .dark
    0.06
    .MONTH
    0.06
     Warp
    0.06
    .Row
    0.06
    Act Density 0.068%

    No Known Activations