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

    Neuronpedia

    INDEX
    Explanations

    To

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hulk
    -0.07
    洁
    -0.06
    ูช
    -0.06
    _annotation
    -0.06
    的人
    -0.06
     неск
    -0.06
    gui
    -0.06
    則
    -0.06
    orb
    -0.06
    .exe
    -0.06
    POSITIVE LOGITS
     To
    0.11
    To
    0.08
     překlad
    0.07
     mga
    0.07
    -To
    0.07
    toMatch
    0.07
    ailure
    0.06
     Antar
    0.06
    uclear
    0.06
    ((_
    0.06
    Act Density 0.019%

    No Known Activations