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

    Neuronpedia

    INDEX
    Explanations

    code/testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _root
    -0.06
     Don
    -0.06
    Pt
    -0.06
    мо
    -0.06
     accountable
    -0.06
    .credit
    -0.06
     Obs
    -0.06
     Braz
    -0.06
     selectedIndex
    -0.06
     loaded
    -0.06
    POSITIVE LOGITS
     сум
    0.07
    arseille
    0.07
    \x
    0.06
     Morales
    0.06
     AND
    0.06
     fer
    0.06
    _public
    0.06
    enguins
    0.06
    明白
    0.06
     들어
    0.06
    Act Density 0.000%

    No Known Activations