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

    Neuronpedia

    INDEX
    Explanations

    Google search URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Desktop
    -0.07
    Unlock
    -0.07
    _figure
    -0.07
    女性
    -0.06
    matches
    -0.06
    lož
    -0.06
     reckless
    -0.06
    LineWidth
    -0.06
     initializing
    -0.06
     Nylon
    -0.06
    POSITIVE LOGITS
    .custom
    0.07
    .CLIENT
    0.07
     onCreateOptionsMenu
    0.06
    pellier
    0.06
    ='%
    0.06
    arlo
    0.06
     İzmir
    0.06
     yaşında
    0.06
     believer
    0.06
     مهند
    0.06
    Act Density 0.013%

    No Known Activations