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

    Neuronpedia

    INDEX
    Explanations

    Indian place names and Q&A formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    puts
    -0.87
    grav
    -0.77
    LOOKUP
    -0.75
    helloworld
    -0.73
    fficacy
    -0.72
     Chaves
    -0.72
    SWE
    -0.71
     Primal
    -0.71
     maxed
    -0.71
    Dyn
    -0.70
    POSITIVE LOGITS
     Assam
    0.82
     Manipur
    0.75
     Arun
    0.75
    ftant
    0.74
     Dima
    0.73
    BitSet
    0.72
    国际
    0.67
     دوم
    0.67
     umbrella
    0.66
    Arun
    0.65
    Act Density 0.028%

    No Known Activations