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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Behavior
    -0.06
    ehir
    -0.06
    _ui
    -0.06
    .dev
    -0.06
     membership
    -0.06
    .WaitFor
    -0.06
    ाउ
    -0.06
    _FILL
    -0.06
    AU
    -0.06
     Ipsum
    -0.06
    POSITIVE LOGITS
    Backing
    0.07
    명을
    0.07
    很多
    0.06
     figsize
    0.06
     onClick
    0.06
    ramework
    0.06
    DateTime
    0.06
     fixes
    0.06
     setting
    0.06
     reproduce
    0.06
    Act Density 0.000%

    No Known Activations