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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nuggets
    -0.08
     getPrice
    -0.07
     ((!
    -0.07
     contrato
    -0.07
     It
    -0.07
     والف
    -0.07
     tabletop
    -0.07
    接触
    -0.06
     FOLLOW
    -0.06
    舶
    -0.06
    POSITIVE LOGITS
     Progressive
    0.08
     Svg
    0.07
    גר
    0.07
     să
    0.07
    syn
    0.07
    Ben
    0.07
    ï
    0.07
    记忆
    0.07
    enti
    0.07
     GUI
    0.07
    Act Density 0.201%

    No Known Activations