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

    Neuronpedia

    INDEX
    Explanations

    introducing items or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wood
    0.49
     describes
    0.44
     timber
    0.44
     tur
    0.42
     sogno
    0.41
     tiveram
    0.41
     david
    0.40
     complications
    0.40
     O
    0.39
     haber
    0.39
    POSITIVE LOGITS
    除去
    0.46
     полиции
    0.44
    씩
    0.43
    国产
    0.42
     Policing
    0.42
    愆
    0.41
    まで
    0.41
    Limits
    0.41
     МВД
    0.41
    ewną
    0.40
    Act Density 0.026%

    No Known Activations