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

    Neuronpedia

    INDEX
    Explanations

    families

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     but
    -0.07
     bridge
    -0.06
     though
    -0.06
     barn
    -0.06
     silicone
    -0.06
     looping
    -0.06
    �
    -0.06
     combustion
    -0.06
    .COMP
    -0.06
     Quad
    -0.06
    POSITIVE LOGITS
    音樂
    0.07
    ertainment
    0.07
    主人
    0.07
    0.07
    DCALL
    0.06
    лем
    0.06
     يجب
    0.06
     GLFW
    0.06
    ledon
    0.06
     SetLastError
    0.06
    Act Density 0.000%

    No Known Activations