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

    Neuronpedia

    INDEX
    Explanations

    units of measurement and their context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    respuesta
    0.45
     spite
    0.44
    ಯ್ಯ
    0.43
     their
    0.42
     दोबारा
    0.42
     thei
    0.40
     the
    0.40
     kivy
    0.39
     ideia
    0.39
     falsehood
    0.39
    POSITIVE LOGITS
    หรือ
    0.60
     или
    0.59
     یا
    0.58
     அல்லது
    0.55
     για
    0.54
     для
    0.53
     ή
    0.53
     =
    0.52
     ≤
    0.52
     hoặc
    0.50
    Act Density 0.026%

    No Known Activations