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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thesize
    -0.07
     Empire
    -0.06
     iterations
    -0.06
    Mes
    -0.06
     polít
    -0.06
     userName
    -0.06
    Scaled
    -0.06
    .IsEmpty
    -0.06
     FIXED
    -0.06
     sought
    -0.06
    POSITIVE LOGITS
    favorites
    0.07
    STD
    0.07
    accordion
    0.07
     všichni
    0.06
    ीव
    0.06
     трь
    0.06
     terug
    0.06
    oints
    0.06
    ront
    0.06
    änn
    0.06
    Act Density 0.035%

    No Known Activations