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

    Neuronpedia

    INDEX
    Explanations

    yourself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生的
    -0.07
     oste
    -0.07
     разреш
    -0.07
     japanese
    -0.06
    coverage
    -0.06
     فوت
    -0.06
     dó
    -0.06
     coquine
    -0.06
    xffffff
    -0.06
     vlan
    -0.06
    POSITIVE LOGITS
     recognizing
    0.08
    ωσε
    0.08
    ABB
    0.07
     increasing
    0.07
     Jamal
    0.06
    VENT
    0.06
    FUL
    0.06
     απο
    0.06
     مفهوم
    0.06
     مث
    0.06
    Act Density 0.008%

    No Known Activations