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

    Neuronpedia

    INDEX
    Explanations

    Asking if reader knows something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     electr
    -0.07
    ané
    -0.07
    (seg
    -0.06
    gnu
    -0.06
    De
    -0.06
     Rob
    -0.06
    Origin
    -0.06
     Std
    -0.06
    Ин
    -0.06
    inium
    -0.06
    POSITIVE LOGITS
     avant
    0.06
    _corners
    0.06
    輯
    0.06
    >w
    0.06
    cm
    0.06
    lač
    0.06
    builder
    0.06
     Civic
    0.06
     gsl
    0.06
    Texas
    0.06
    Act Density 0.014%

    No Known Activations