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

    Neuronpedia

    INDEX
    Explanations

    Test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.75
    findpost
    -0.74
     ويكيميديا
    -0.65
    unhofer
    -0.63
    amaño
    -0.60
    NOPQRST
    -0.59
    igrette
    -0.58
     AssemblyCompany
    -0.57
    DockStyle
    -0.56
    quelize
    -0.54
    POSITIVE LOGITS
     bodies
    0.63
     to
    0.57
     Lordships
    0.55
     coats
    0.52
     mouths
    0.50
    bodies
    0.49
    Tembelea
    0.48
     AttributeSet
    0.47
    invokeLater
    0.47
     uniforms
    0.47
    Act Density 0.000%

    No Known Activations