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

    Neuronpedia

    INDEX
    Explanations

    Thai, Indian, or Mongolian context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verv
    0.57
     Bout
    0.56
    Middleware
    0.55
    ärk
    0.55
    etano
    0.54
     Aktion
    0.53
     Islamist
    0.53
     packed
    0.53
     jest
    0.52
     اح
    0.51
    POSITIVE LOGITS
    ph
    0.71
    pho
    0.61
     ph
    0.60
    pt
    0.60
    rt
    0.59
    rti
    0.59
    orsion
    0.59
    sores
    0.59
    ht
    0.59
    gt
    0.57
    Act Density 0.022%

    No Known Activations