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

    Neuronpedia

    INDEX
    Explanations

    .*\;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    031
    -0.06
     afin
    -0.06
     lm
    -0.06
     Carey
    -0.06
     ''),
    -0.06
     stren
    -0.06
    σκεται
    -0.06
     Winner
    -0.06
     function
    -0.06
     fold
    -0.06
    POSITIVE LOGITS
    .*;↵
    0.11
    .*;↵↵
    0.10
    /embed
    0.07
    ipl
    0.07
     tournaments
    0.06
    iances
    0.06
    ใต
    0.06
    .props
    0.06
    learning
    0.06
    doing
    0.06
    Act Density 0.001%

    No Known Activations