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

    Neuronpedia

    INDEX
    Explanations

    say "definition"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flash
    -0.07
    归来
    -0.07
    alphabet
    -0.07
    )!
    -0.07
     coz
    -0.06
     Nest
    -0.06
     Twice
    -0.06
     hư
    -0.06
     please
    -0.06
     economía
    -0.06
    POSITIVE LOGITS
     ancor
    0.07
    仍旧
    0.07
     bom
    0.07
    Framework
    0.07
    تماع
    0.06
    _countries
    0.06
     uppercase
    0.06
    KeyListener
    0.06
     sout
    0.06
    湴
    0.06
    Act Density 0.016%

    No Known Activations