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

    Neuronpedia

    INDEX
    Explanations

    Lowering movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ommen
    -0.06
     Lect
    -0.06
    ören
    -0.06
    _hour
    -0.06
    loff
    -0.06
     fashion
    -0.06
     cca
    -0.06
     pie
    -0.06
     milk
    -0.06
     Mae
    -0.06
    POSITIVE LOGITS
     preamble
    0.07
    ุงเทพมหานคร
    0.06
     safezone
    0.06
    疗
    0.06
    AREA
    0.06
    .pen
    0.06
     proficiency
    0.06
    uther
    0.06
     olmayan
    0.06
     poprvé
    0.06
    Act Density 0.056%

    No Known Activations