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

    Neuronpedia

    INDEX
    Explanations

    referring to user's questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     служ
    0.63
    ową
    0.59
     völl
    0.52
    álló
    0.52
     семь
    0.51
     captives
    0.51
     linkCell
    0.49
    𝟭
    0.49
     Angebote
    0.49
     Basta
    0.48
    POSITIVE LOGITS
    cycl
    0.43
     mathematics
    0.42
    circular
    0.42
    TEM
    0.41
    ttore
    0.40
    cin
    0.39
    declar
    0.39
    此外
    0.38
    weighted
    0.38
    чена
    0.38
    Act Density 0.003%

    No Known Activations