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

    Neuronpedia

    INDEX
    Explanations

    Code, news, technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     varandra
    -0.66
    Mip
    -0.59
    MemoryWarning
    -0.58
    뀌
    -0.56
    TestBed
    -0.54
    مصادر
    -0.54
    cjon
    -0.54
     trás
    -0.54
    inander
    -0.53
    xically
    -0.53
    POSITIVE LOGITS
     виправивши
    0.64
    tagHelperRunner
    0.58
    PathVariable
    0.56
    igshid
    0.54
    fjspx
    0.53
    раздо
    0.52
     MainAxisSize
    0.52
     Granville
    0.51
    Predecesor
    0.49
    XmlAccessType
    0.49
    Act Density 0.001%

    No Known Activations