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

    Neuronpedia

    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.87
     препратки
    -0.82
     AssemblyProduct
    -0.79
     مشين
    -0.79
     saites
    -0.76
    RegressionTest
    -0.75
     חיצוניים
    -0.75
     متعلقه
    -0.74
    TemporalType
    -0.73
    ThroughAttribute
    -0.73
    POSITIVE LOGITS
     mystique
    0.45
     IOError
    0.41
    worldly
    0.40
    do
    0.39
     martyrdom
    0.38
    nyard
    0.37
    Segue
    0.37
     apocalypse
    0.37
    ultimate
    0.36
    s
    0.36
    Act Density 0.001%

    No Known Activations