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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Кла
    0.53
     one
    0.52
     two
    0.52
     on
    0.51
     ص
    0.49
    ای
    0.47
    αυ
    0.47
     a
    0.47
    լ
    0.47
    С
    0.46
    POSITIVE LOGITS
    and
    0.52
    나
    0.46
    nante
    0.46
     BUFFER
    0.45
     ADDRESS
    0.44
     Capability
    0.44
     করুন
    0.44
     करेगा
    0.43
     தரும்
    0.43
    ation
    0.43
    Act Density 0.053%

    No Known Activations