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

    Neuronpedia

    INDEX
    Explanations

    code structure or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     well
    0.72
     pro
    0.70
     also
    0.67
     beyond
    0.66
     emerging
    0.63
     won
    0.62
     patent
    0.61
     extra
    0.60
     au
    0.59
     elsewhere
    0.59
    POSITIVE LOGITS
    örper
    0.75
     Số
    0.75
    ንዳንድ
    0.73
     Estoy
    0.72
    𝚕
    0.72
    currentIndex
    0.70
    шое
    0.70
    ॉय
    0.70
     университета
    0.70
     Университе
    0.69
    Act Density 0.059%

    No Known Activations