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

    Neuronpedia

    INDEX
    Explanations

    self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	TokenName
    -0.07
    .inventory
    -0.07
    \Collections
    -0.07
     Loving
    -0.06
    noteq
    -0.06
     CGRectMake
    -0.06
    Reached
    -0.06
    concat
    -0.06
     vmax
    -0.06
    getDrawable
    -0.06
    POSITIVE LOGITS
    fred
    0.07
    oodles
    0.07
     physics
    0.07
     glu
    0.06
    sci
    0.06
     APIs
    0.06
     gli
    0.06
    ifes
    0.06
    (["
    0.06
     containers
    0.06
    Act Density 0.001%

    No Known Activations