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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stu
    -0.64
     Stu
    -0.63
    ergic
    -0.56
    Stu
    -0.56
     mon
    -0.53
    GLenum
    -0.51
    saraba
    -0.50
     initView
    -0.47
    +#+
    -0.46
     plunger
    -0.45
    POSITIVE LOGITS
    webElementXpaths
    0.71
     EconPapers
    0.63
    DockStyle
    0.62
    IsMutable
    0.58
    Personensuche
    0.54
    hdys
    0.53
    WriteAttribute
    0.50
     pauvreté
    0.50
    des
    0.50
    ⓧ
    0.50
    Act Density 0.007%

    No Known Activations