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

    Neuronpedia

    INDEX
    Explanations

    mathematical problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     level
    -0.08
     erzielen
    -0.08
     flor
    -0.08
     pozi
    -0.07
    _SIMPLE
    -0.07
    _COLOR
    -0.07
     livello
    -0.07
     hoa
    -0.07
    003
    -0.07
     Fabric
    -0.07
    POSITIVE LOGITS
    Duration
    0.17
     duration
    0.17
     durations
    0.17
    .Duration
    0.17
    duration
    0.16
    _seconds
    0.16
    .duration
    0.16
     Duration
    0.16
    _duration
    0.16
     stopwatch
    0.16
    Act Density 0.163%

    No Known Activations