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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acheter
    -0.07
    इस
    -0.07
    たし
    -0.06
    etween
    -0.06
     secretary
    -0.06
    sse
    -0.06
     Boise
    -0.06
    sam
    -0.06
     HTC
    -0.06
     üy
    -0.05
    POSITIVE LOGITS
    ταση
    0.07
    Anal
    0.07
    _${
    0.07
    ава
    0.07
     subscribers
    0.06
    (receiver
    0.06
    -ves
    0.06
     Anal
    0.06
     Mathematics
    0.06
     modifiers
    0.06
    Act Density 0.035%

    No Known Activations