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

    Neuronpedia

    INDEX
    Explanations

    app component selector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    මුත්
    0.48
    젹
    0.43
    CollectedField
    0.41
    AuthProvider
    0.41
    mpa
    0.40
    ıyorum
    0.39
    multiSelectList
    0.39
     מז
    0.38
     nutrit
    0.38
    serviceTime
    0.38
    POSITIVE LOGITS
    hammer
    0.47
     browser
    0.44
    browser
    0.44
    platform
    0.44
     forms
    0.44
    forms
    0.42
    Hammer
    0.41
     forme
    0.40
    sche
    0.40
    CD
    0.39
    Act Density 0.002%

    No Known Activations