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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oque
    -0.07
    ulet
    -0.07
    Bern
    -0.06
    vik
    -0.06
    vide
    -0.06
    cadena
    -0.06
    spir
    -0.06
    finity
    -0.06
    -saving
    -0.06
    vided
    -0.06
    POSITIVE LOGITS
     licked
    0.07
     тщ
    0.06
    ैज
    0.06
     Luật
    0.06
     adequ
    0.06
     hmot
    0.06
    ايش
    0.06
    _translate
    0.06
     hair
    0.06
     COPYRIGHT
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.