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

    Neuronpedia

    INDEX
    Explanations

    website excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    라마
    -0.06
    sth
    -0.06
     Ô
    -0.06
     respectful
    -0.06
    -third
    -0.06
    tres
    -0.06
     Heroes
    -0.06
    птом
    -0.06
     Minute
    -0.06
    NN
    -0.06
    POSITIVE LOGITS
     geo
    0.07
    权限
    0.06
     notifying
    0.06
     disappe
    0.06
     ekonom
    0.06
     capped
    0.06
    �
    0.06
    >-->↵
    0.06
     Cavaliers
    0.06
     someone
    0.06
    Act Density 0.022%

    No Known Activations