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

    Neuronpedia

    INDEX
    Explanations

    McConnell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zorun
    -0.07
     furthermore
    -0.07
     #[
    -0.06
     сосуд
    -0.06
    _word
    -0.06
    792
    -0.06
     fileName
    -0.06
    .capitalize
    -0.06
    "[
    -0.06
     stick
    -0.06
    POSITIVE LOGITS
     ESL
    0.07
    inactive
    0.07
    umatic
    0.07
    Disabled
    0.06
    violent
    0.06
    .Alignment
    0.06
    mav
    0.06
    ائی
    0.06
    0.06
    -controlled
    0.06
    Act Density 0.032%

    No Known Activations