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

    Neuronpedia

    INDEX
    Explanations

    pension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     above
    -0.07
     Gret
    -0.07
    feof
    -0.07
    _detected
    -0.07
    enuous
    -0.07
    _glyph
    -0.07
    upon
    -0.07
     abandoned
    -0.07
    野外
    -0.07
    祐
    -0.07
    POSITIVE LOGITS
    -law
    0.07
     очередь
    0.07
    roat
    0.07
    curities
    0.07
    oins
    0.06
     cravings
    0.06
     securities
    0.06
    greso
    0.06
    orks
    0.06
    oes
    0.06
    Act Density 0.002%

    No Known Activations