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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilecek
    -0.07
    -xl
    -0.07
     oluyor
    -0.07
    ibel
    -0.07
    ivals
    -0.07
     그렇
    -0.07
    .TODO
    -0.07
    就会
    -0.07
    production
    -0.06
    ویش
    -0.06
    POSITIVE LOGITS
    (PropertyName
    0.06
     een
    0.06
     suck
    0.06
     bona
    0.06
     tty
    0.06
    bd
    0.06
    (in
    0.06
    $PostalCodesNL
    0.06
     Fed
    0.06
    $order
    0.06
    Act Density 0.088%

    No Known Activations