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

    Neuronpedia

    INDEX
    Explanations

    C++ code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    release
    0.46
    cleanup
    0.46
     cleanup
    0.46
    ransom
    0.43
    释放
    0.43
    axial
    0.43
    rison
    0.42
    destroy
    0.42
    housing
    0.42
    waf
    0.41
    POSITIVE LOGITS
    恈
    0.42
    하였다
    0.41
     Prz
    0.40
    桥
    0.39
     לצ
    0.38
    廖
    0.38
     문
    0.38
     WALKER
    0.38
    曏
    0.38
     இல்லாமல்
    0.37
    Act Density 0.001%

    No Known Activations