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

    Neuronpedia

    INDEX
    Explanations

    equating or considering value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Runtime
    0.45
     Happen
    0.44
     specifics
    0.44
    これは
    0.44
     Detailed
    0.42
     বৃহৎ
    0.42
     CUDA
    0.41
     Trusted
    0.41
     UUID
    0.41
    リアル
    0.40
    POSITIVE LOGITS
     overrated
    0.69
     synonymous
    0.60
     equated
    0.54
     underrated
    0.54
     tantamount
    0.53
     objectively
    0.51
     equivalente
    0.50
    considered
    0.50
     detrimental
    0.49
     considered
    0.49
    Act Density 0.323%

    No Known Activations