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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seperti
    -0.07
     addicts
    -0.06
     цер
    -0.06
    Liter
    -0.06
     rooms
    -0.06
     apa
    -0.06
    羅
    -0.06
     }}}
    -0.06
    ilon
    -0.06
    ё
    -0.06
    POSITIVE LOGITS
    events
    0.07
    ademic
    0.07
    LN
    0.06
     scrolled
    0.06
    BN
    0.06
     progn
    0.06
     instanceof
    0.06
     Michele
    0.06
     Tele
    0.06
     Paginator
    0.06
    Act Density 0.000%

    No Known Activations