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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flushed
    -0.07
    isy
    -0.07
    -0.06
    ros
    -0.06
     Boris
    -0.06
    飾
    -0.06
     Violet
    -0.06
    xFA
    -0.06
    -0.06
     cropped
    -0.06
    POSITIVE LOGITS
    _media
    0.07
     sonrası
    0.06
    _tcb
    0.06
     Hunger
    0.06
    owering
    0.06
    istrov
    0.06
     {{--<
    0.06
     ход
    0.06
     Instruction
    0.06
    .Sql
    0.06
    Act Density 0.155%

    No Known Activations