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

    Neuronpedia

    INDEX
    Explanations

    Latvian, latkes, latte, Lattner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poor
    0.40
    ታት
    0.37
     emotional
    0.37
    coma
    0.37
     employers
    0.37
    lion
    0.36
    llium
    0.36
    poor
    0.35
    শুভ
    0.35
     Teachers
    0.34
    POSITIVE LOGITS
     lat
    0.69
    Lat
    0.69
     latt
    0.60
     LAT
    0.59
     LT
    0.57
     Lat
    0.54
    LAT
    0.53
    lat
    0.52
    olat
    0.50
     LTC
    0.49
    Act Density 0.007%

    No Known Activations