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

    Neuronpedia

    INDEX
    Explanations

    text completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    χρι
    0.44
    衆
    0.37
     хочет
    0.37
    feels
    0.37
     Trucks
    0.37
    唯一的
    0.36
     הב
    0.36
    Mis
    0.35
    стрее
    0.35
     Viele
    0.35
    POSITIVE LOGITS
     equivalent
    0.57
     wide
    0.55
     large
    0.55
     extremes
    0.54
     equivalents
    0.53
     detailed
    0.52
     enormous
    0.52
     enorme
    0.52
     complete
    0.50
     stark
    0.49
    Act Density 0.001%

    No Known Activations