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

    Neuronpedia

    INDEX
    Explanations

    Points and miles redemption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embry
    -0.07
     Stephens
    -0.07
    سير
    -0.07
    Prince
    -0.07
    ampionship
    -0.07
    embourg
    -0.07
     банков
    -0.07
     chickens
    -0.07
     pounds
    -0.07
     PublicKey
    -0.07
    POSITIVE LOGITS
    开荒
    0.08
    ◖
    0.07
    𝙏
    0.07
    嗜
    0.07
     flags
    0.07
    衰
    0.07
    hazi
    0.07
    🛬
    0.07
    ﮋ
    0.07
    _apply
    0.06
    Act Density 0.021%

    No Known Activations