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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endedor
    -0.07
     찾아
    -0.07
     техніч
    -0.06
    ンド
    -0.06
    .SceneManagement
    -0.06
    лася
    -0.06
     aktar
    -0.06
    portrait
    -0.06
     embroidered
    -0.06
     Regents
    -0.06
    POSITIVE LOGITS
     superheroes
    0.07
     when
    0.07
     Heck
    0.06
     hoof
    0.06
    др
    0.06
    .dict
    0.06
     وقد
    0.06
     روست
    0.06
     (;;
    0.05
    :l
    0.05
    Act Density 0.032%

    No Known Activations