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

    Neuronpedia

    INDEX
    Explanations

    Code/text fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “He
    -0.07
    üyle
    -0.07
    _he
    -0.07
     bmp
    -0.06
     Asians
    -0.06
     swo
    -0.06
    InThe
    -0.06
     خو
    -0.06
    HomeAs
    -0.06
    .progressBar
    -0.06
    POSITIVE LOGITS
    üh
    0.06
    .userData
    0.06
     接
    0.06
     bogus
    0.06
    PROC
    0.06
     illusions
    0.06
    −
    0.06
     moder
    0.06
     болезни
    0.06
    /common
    0.06
    Act Density 0.029%

    No Known Activations