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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alternating
    -0.07
    796
    -0.07
    =@
    -0.06
    ('.',
    -0.06
    .ctx
    -0.06
     důsled
    -0.06
    łu
    -0.06
    iam
    -0.06
     tròn
    -0.06
     Cultural
    -0.06
    POSITIVE LOGITS
    $args
    0.07
    ême
    0.06
    чук
    0.06
     unravel
    0.06
     ).
    0.06
     Kale
    0.06
     <<<
    0.06
     babel
    0.06
     textBox
    0.06
    �
    0.06
    Act Density 0.027%

    No Known Activations