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

    Neuronpedia

    INDEX
    Explanations

    comma or hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urances
    -0.08
     avenues
    -0.07
    _age
    -0.07
     приготовления
    -0.07
     الذه
    -0.06
    _pipe
    -0.06
     larg
    -0.06
    _outputs
    -0.06
     originated
    -0.06
     spect
    -0.06
    POSITIVE LOGITS
    \-
    0.07
    ++)↵
    0.07
    ;<
    0.07
    (Transform
    0.06
     Sokol
    0.06
    ').'</
    0.06
    $:
    0.06
    積
    0.06
    (Graphics
    0.06
     Algebra
    0.06
    Act Density 0.006%

    No Known Activations