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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BLACK
    -0.07
    .project
    -0.06
     терап
    -0.06
     Frage
    -0.06
     хлоп
    -0.06
     forgotten
    -0.06
     Better
    -0.06
     PL
    -0.06
     woodland
    -0.06
    ATAR
    -0.06
    POSITIVE LOGITS
    |i
    0.07
     Dad
    0.07
     Disney
    0.07
     meets
    0.07
    NetMessage
    0.06
    Grab
    0.06
    мини
    0.06
    ати
    0.06
    ----------
↵
    0.06
     Jasper
    0.06
    Act Density 0.000%

    No Known Activations