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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diagrams
    -0.07
     ql
    -0.06
    lings
    -0.06
    허
    -0.06
    asy
    -0.06
     logistic
    -0.06
    ्पत
    -0.06
     As
    -0.06
     motors
    -0.06
    prop
    -0.06
    POSITIVE LOGITS
    JE
    0.08
     acompañ
    0.07
    지를
    0.07
    ('-
    0.07
    olet
    0.07
     marzo
    0.07
     obed
    0.07
     花
    0.06
     meticulously
    0.06
    Drv
    0.06
    Act Density 0.028%

    No Known Activations