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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adox
    -0.07
    Triangles
    -0.07
     MT
    -0.06
    density
    -0.06
    adt
    -0.06
    Eq
    -0.06
     cols
    -0.06
    TINGS
    -0.06
    橋
    -0.06
     devices
    -0.06
    POSITIVE LOGITS
     His
    0.08
    His
    0.07
     研
    0.07
     Her
    0.07
     Veranst
    0.07
     his
    0.07
     Hispan
    0.07
     your
    0.07
     Giám
    0.07
     خود
    0.06
    Act Density 0.017%

    No Known Activations