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

    Neuronpedia

    INDEX
    Explanations

    neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jam
    -0.07
    urther
    -0.07
     threaten
    -0.07
    ことです
    -0.06
     sigue
    -0.06
    豬
    -0.06
    聚焦
    -0.06
    ITHER
    -0.06
     characterize
    -0.06
    elige
    -0.06
    POSITIVE LOGITS
     Objects
    0.07
    -policy
    0.07
    -reset
    0.07
     móvil
    0.07
    -frame
    0.07
    一千
    0.06
    oplan
    0.06
    -object
    0.06
     Ав
    0.06
     Programm
    0.06
    Act Density 0.029%

    No Known Activations