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

    Neuronpedia

    INDEX
    Explanations

    video that, have the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ï½°
    -0.11
    _Tis
    -0.10
     меÑĤалли
    -0.10
    togroup
    -0.09
    isContained
    -0.09
     fitte
    -0.09
    chandle
    -0.09
     appearances
    -0.09
    _Lean
    -0.09
    ----------</
    -0.09
    POSITIVE LOGITS
     task
    0.20
     topic
    0.19
     project
    0.16
     scenario
    0.16
     story
    0.16
     event
    0.15
    ä»»åĬ¡
    0.15
    é¢ĺ
    0.15
    task
    0.14
     episode
    0.14
    Act Density 1.885%

    No Known Activations