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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áng
    -0.07
    engineering
    -0.07
    реж
    -0.06
     Wallet
    -0.06
    (mode
    -0.06
    Global
    -0.06
    <label
    -0.06
    cargo
    -0.06
    (Paint
    -0.06
    ột
    -0.06
    POSITIVE LOGITS
     Kate
    0.07
     competed
    0.06
     Не
    0.06
    �
    0.06
    edere
    0.05
     Oklahoma
    0.05
    306
    0.05
     chy
    0.05
    StatusCode
    0.05
     TRY
    0.05
    Act Density 0.019%

    No Known Activations