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

    Neuronpedia

    INDEX
    Explanations

    C++ and C# programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    拈
    0.63
     distributed
    0.62
     fell
    0.62
     disbursed
    0.62
     HSC
    0.60
    umptions
    0.60
     thc
    0.59
    ilable
    0.59
     debated
    0.58
    いただきました
    0.58
    POSITIVE LOGITS
     C
    0.89
    ++
    0.85
    IG
    0.75
    eper
    0.75
    TP
    0.75
    C
    0.74
    ITS
    0.73
    IMP
    0.73
    OTS
    0.72
    ITI
    0.72
    Act Density 0.048%

    No Known Activations