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

    Neuronpedia

    INDEX
    Explanations

    Is it possible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diff
    -0.08
     diff
    -0.07
    ỉ
    -0.07
     frustrated
    -0.06
     Page
    -0.06
    只是
    -0.06
    _Draw
    -0.06
    .block
    -0.06
    ڳ
    -0.06
     tờ
    -0.06
    POSITIVE LOGITS
     предлаг
    0.08
    ulnerable
    0.07
    (compact
    0.07
    ☹
    0.07
     FUN
    0.07
    	sw
    0.07
     terme
    0.07
    .say
    0.07
     Atl
    0.07
    <Model
    0.07
    Act Density 0.233%

    No Known Activations