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

    Neuronpedia

    INDEX
    Explanations

    goals or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    0.58
     people
    0.54
    ار
    0.54
     persones
    0.47
     penge
    0.46
     در
    0.45
     फक्त
    0.44
     carelessness
    0.43
     保護
    0.43
    ”，
    0.43
    POSITIVE LOGITS
    radial
    0.53
    drag
    0.50
    Comparable
    0.48
    Trent
    0.48
     Trent
    0.48
    elevation
    0.48
    credentials
    0.47
    überkü
    0.47
    ług
    0.47
    develop
    0.46
    Act Density 0.001%

    No Known Activations