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

    Neuronpedia

    INDEX
    Explanations

    c++ code with include

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sens
    0.71
    fas
    0.67
     পাচ্ছে
    0.64
    していて
    0.63
     nui
    0.62
     launching
    0.61
    も見
    0.61
     issued
    0.61
     lowers
    0.61
     resulting
    0.60
    POSITIVE LOGITS
    define
    2.21
     define
    1.77
    ifdef
    1.66
    pragma
    1.63
    include
    1.58
    ifndef
    1.54
     Define
    1.48
     redefine
    1.36
    Define
    1.35
    endif
    1.35
    Act Density 0.032%

    No Known Activations