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

    Neuronpedia

    INDEX
    Explanations

    202

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _linear
    -0.07
    ож
    -0.06
     HttpMethod
    -0.06
    نا
    -0.06
    Child
    -0.06
    _HANDLER
    -0.06
    hp
    -0.06
    conditional
    -0.06
     sg
    -0.06
    шло
    -0.06
    POSITIVE LOGITS
     Xt
    0.07
    社区
    0.07
    wdx
    0.06
     설치
    0.06
     Bài
    0.06
     Donne
    0.06
    Japan
    0.06
     ของ
    0.06
    Reviewer
    0.06
    402
    0.06
    Act Density 0.004%

    No Known Activations