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
     Ranch
    -0.07
    spots
    -0.07
    "}}↵
    -0.07
    cube
    -0.07
     grain
    -0.06
     []);↵↵
    -0.06
     summer
    -0.06
    _Search
    -0.06
     aç
    -0.06
     Hack
    -0.06
    POSITIVE LOGITS
     GENER
    0.06
     далеко
    0.06
    dü
    0.06
     glorious
    0.06
    _ARGS
    0.06
    .eql
    0.06
    IMATION
    0.06
     WAS
    0.06
     stagn
    0.06
     وي
    0.06
    Act Density 0.162%

    No Known Activations