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

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('\\
    -0.08
    Lifetime
    -0.07
     wine
    -0.06
     dinners
    -0.06
     boarding
    -0.06
    ?>
↵
↵
    -0.06
     wounded
    -0.06
    沉
    -0.06
     upstairs
    -0.06
    _TRIANGLE
    -0.06
    POSITIVE LOGITS
     Stores
    0.07
     Configure
    0.07
     CC
    0.06
    �에
    0.06
     LANG
    0.06
     /**↵
    0.06
     Teuchos
    0.06
     Center
    0.06
    кі
    0.06
    <center
    0.06
    Act Density 0.002%

    No Known Activations