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

    Neuronpedia

    INDEX
    Explanations

    code and syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diesel
    -0.07
    Constraint
    -0.07
     ASSERT
    -0.07
     Manage
    -0.06
     Bears
    -0.06
     withdrawal
    -0.06
     VIEW
    -0.06
     securities
    -0.06
    Busy
    -0.06
    EQ
    -0.06
    POSITIVE LOGITS
    ，从
    0.06
     Ả
    0.06
     ruta
    0.06
     ❤
    0.06
    Veter
    0.06
     tud
    0.06
    LIGHT
    0.06
    λος
    0.06
     läng
    0.05
     מ
    0.05
    Act Density 0.162%

    No Known Activations