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

    Neuronpedia

    INDEX
    Explanations

    relative and relatively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essentiellement
    0.48
     entièrement
    0.42
    adjacency
    0.40
    ]]:
    0.40
     арен
    0.40
     vermutlich
    0.39
    ون
    0.38
    ]):
    0.38
     upgraded
    0.38
     entirely
    0.38
    POSITIVE LOGITS
     Relative
    0.73
    relative
    0.63
    相对
    0.62
     newcomer
    0.62
     relative
    0.61
    相対
    0.59
    Relative
    0.59
     relatively
    0.56
    نسب
    0.55
    相對
    0.55
    Act Density 0.009%

    No Known Activations