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

    Neuronpedia

    INDEX
    Explanations

    Setting Ideas, Examples, crucial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    0.52
    Health
    0.45
     Health
    0.44
    鹬
    0.44
    flo
    0.43
    bö
    0.42
    Clone
    0.42
     Krank
    0.41
    School
    0.41
     Clone
    0.40
    POSITIVE LOGITS
    ्स
    0.54
    ामो
    0.51
    0.48
     നമഃ
    0.46
     sockets
    0.46
     events
    0.44
     evento
    0.44
     avenues
    0.44
    socketState
    0.44
     arguments
    0.44
    Act Density 0.003%

    No Known Activations