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

    Neuronpedia

    INDEX
    Explanations

    Figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chick
    -0.08
     circa
    -0.07
     Mama
    -0.07
    Startup
    -0.07
     ayant
    -0.07
    /state
    -0.07
     mount
    -0.07
     Dorothy
    -0.07
    .amount
    -0.07
     textSize
    -0.07
    POSITIVE LOGITS
    боль
    0.07
    լ
    0.07
    .board
    0.07
     brutality
    0.07
    维修
    0.07
    国外
    0.06
    endimento
    0.06
    .br
    0.06
    -del
    0.06
    .controllers
    0.06
    Act Density 0.004%

    No Known Activations