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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xmax
    -0.07
     kø
    -0.07
    Nama
    -0.07
     Suarez
    -0.06
    )}>
    -0.06
    yaw
    -0.06
    edula
    -0.06
    marginTop
    -0.06
    roleum
    -0.06
     público
    -0.06
    POSITIVE LOGITS
     зрения
    0.07
     Accept
    0.06
     apex
    0.06
     dinners
    0.06
     urgent
    0.06
     accepts
    0.06
     CAD
    0.06
     nationwide
    0.06
     stability
    0.06
     Patty
    0.06
    Act Density 0.007%

    No Known Activations