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

    Neuronpedia

    INDEX
    Explanations

    purpose, global, always, been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ა
    0.44
     सुद्धा
    0.44
    cis
    0.43
    t
    0.42
     couple
    0.42
    each
    0.41
     Reihe
    0.40
     distanciation
    0.40
     gedaan
    0.40
    the
    0.40
    POSITIVE LOGITS
     solos
    0.46
     गारंटर
    0.46
     oxides
    0.46
    getStartState
    0.45
     到
    0.45
     vacations
    0.45
     acuerdos
    0.45
     envisions
    0.44
     pavilions
    0.44
    BeerItem
    0.44
    Act Density 0.000%

    No Known Activations