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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .toFloat
    -0.06
     Erect
    -0.06
    обов
    -0.06
    На
    -0.06
     Wii
    -0.06
    AMI
    -0.06
     ย
    -0.06
    COMMAND
    -0.06
    一緒
    -0.06
    yi
    -0.06
    POSITIVE LOGITS
    :set
    0.07
     problematic
    0.07
     (?
    0.07
     consistent
    0.07
     doom
    0.06
     keeper
    0.06
    .horizontal
    0.06
     colder
    0.06
    _slider
    0.06
    ereum
    0.06
    Act Density 1.442%

    No Known Activations