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

    Neuronpedia

    INDEX
    Explanations

    code or technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frauen
    -0.07
    “These
    -0.06
    "These
    -0.06
     Mend
    -0.06
     entreg
    -0.06
     Graduate
    -0.06
    ังหว
    -0.06
     Naughty
    -0.06
    ευση
    -0.06
     cười
    -0.06
    POSITIVE LOGITS
    �
    0.07
     educators
    0.06
     mug
    0.06
     б
    0.06
    /dialog
    0.06
    /object
    0.06
     grou
    0.06
    اف
    0.06
     heck
    0.06
     clr
    0.06
    Act Density 0.001%

    No Known Activations