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

    Neuronpedia

    INDEX
    Explanations

    code and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReuseIdentifier
    -0.07
     Sahara
    -0.06
     �
    -0.06
    uenta
    -0.06
     руки
    -0.06
     ")[
    -0.06
     giữa
    -0.06
     isArray
    -0.06
     Brief
    -0.06
    ^[
    -0.06
    POSITIVE LOGITS
    estli
    0.07
    ну
    0.07
    phi
    0.07
    tower
    0.06
    ポ
    0.06
    戲
    0.06
     neglig
    0.06
    b
    0.06
    rix
    0.06
    glm
    0.06
    Act Density 0.000%

    No Known Activations