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

    Neuronpedia

    INDEX
    Explanations

    dangerous activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disability
    0.52
     tattoos
    0.48
     expectations
    0.47
     distortions
    0.47
     disabilities
    0.46
     vag
    0.45
     hills
    0.44
    qual
    0.43
     bandages
    0.43
     patterns
    0.43
    POSITIVE LOGITS
    нт
    0.54
    mLogin
    0.54
    lw
    0.48
     للمعارف
    0.48
    ф
    0.47
    alai
    0.47
    АН
    0.46
    larının
    0.46
     വല
    0.46
    роне
    0.46
    Act Density 0.001%

    No Known Activations