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

    Neuronpedia

    INDEX
    Explanations

    political leanings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leading
    -0.07
     EDUC
    -0.07
     пи
    -0.07
     י
    -0.07
    בסיס
    -0.07
    .IsNotNull
    -0.07
    _IV
    -0.07
    (styles
    -0.06
     Perform
    -0.06
     devised
    -0.06
    POSITIVE LOGITS
    횔
    0.07
     shorts
    0.07
     שלך
    0.07
    rollable
    0.07
    됬
    0.07
    _CAL
    0.07
     releases
    0.07
    :"-
    0.06
    側
    0.06
    ffc
    0.06
    Act Density 0.063%

    No Known Activations