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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urnya
    0.64
    স্ফ
    0.62
     generaciones
    0.62
    run
    0.61
    oked
    0.61
    navigate
    0.60
    urt
    0.60
     मांग
    0.60
    opath
    0.60
    先輩
    0.59
    POSITIVE LOGITS
     lacks
    0.59
     directed
    0.59
     Back
    0.58
     Working
    0.57
    كيل
    0.56
     backlog
    0.55
     surface
    0.55
     manual
    0.55
    mith
    0.54
     TAM
    0.54
    Act Density 0.095%

    No Known Activations