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

    Neuronpedia

    INDEX
    Explanations

    rearranging expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    saldo
    -0.07
    ]),↵
    -0.06
     GLFW
    -0.06
     Worst
    -0.06
    guide
    -0.06
    .flow
    -0.06
    School
    -0.06
    vida
    -0.06
    甚
    -0.06
    .Y
    -0.06
    POSITIVE LOGITS
     relocated
    0.08
     reorder
    0.07
    emales
    0.06
    打开
    0.06
    ooke
    0.06
     Nurse
    0.06
     reordered
    0.06
    .newBuilder
    0.06
    shuffle
    0.06
    .Alignment
    0.06
    Act Density 0.006%

    No Known Activations