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

    Neuronpedia

    INDEX
    Explanations

    technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decks
    -0.06
     ®
    -0.06
    تم
    -0.06
     συν
    -0.06
    _TRACK
    -0.06
    aised
    -0.06
    _border
    -0.06
     bondage
    -0.06
    ení
    -0.06
    ати
    -0.06
    POSITIVE LOGITS
    /Test
    0.07
    creates
    0.07
    /load
    0.06
     truths
    0.06
    spaces
    0.06
    .cloud
    0.06
    proc
    0.06
    _ut
    0.06
    update
    0.06
    rompt
    0.06
    Act Density 0.000%

    No Known Activations