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

    Neuronpedia

    INDEX
    Explanations

    looking down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Possibly
    -0.07
     kone
    -0.07
     नई
    -0.07
    她的
    -0.06
    дами
    -0.06
     تول
    -0.06
     afforded
    -0.06
    เย
    -0.06
     Constant
    -0.06
    υχ
    -0.06
    POSITIVE LOGITS
    减
    0.07
     POSITION
    0.07
     oxidation
    0.06
     Awakening
    0.06
     公
    0.06
     getDate
    0.06
    ฟ
    0.06
    減
    0.06
    选
    0.06
    260
    0.06
    Act Density 0.003%

    No Known Activations