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

    Neuronpedia

    INDEX
    Explanations

    _module

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .'),↵
    -0.07
    "--
    -0.06
    ({})↵
    -0.06
    Pop
    -0.06
    ]';↵
    -0.06
    __))
    -0.06
    واء
    -0.06
    }");
↵
    -0.06
     ():
    -0.06
    Special
    -0.06
    POSITIVE LOGITS
    throp
    0.07
    ilden
    0.07
     awaken
    0.06
     Felix
    0.06
    isses
    0.06
     threw
    0.06
     dress
    0.06
    vůli
    0.06
     deix
    0.06
    voor
    0.06
    Act Density 0.000%

    No Known Activations