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

    Neuronpedia

    INDEX
    Explanations

    INGS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٸ
    -0.08
     Costco
    -0.07
    world
    -0.07
     nbytes
    -0.07
     Psych
    -0.07
     anymore
    -0.07
    IfExists
    -0.06
     >
    -0.06
    as
    -0.06
    _OPTS
    -0.06
    POSITIVE LOGITS
     jointly
    0.07
     agreed
    0.07
    贽
    0.06
    nette
    0.06
     stringWithFormat
    0.06
    tection
    0.06
     график
    0.06
    柩
    0.06
     Saf
    0.06
     strengthen
    0.06
    Act Density 0.002%

    No Known Activations