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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UN
    -0.07
     fitness
    -0.07
    -eff
    -0.07
    的趋势
    -0.07
    撑
    -0.07
    _fr
    -0.07
    EP
    -0.07
    SUP
    -0.07
    \x
    -0.07
     Ed
    -0.07
    POSITIVE LOGITS
    찰
    0.07
    🗨
    0.07
     Việc
    0.06
    Scripts
    0.06
    融资
    0.06
     anmeld
    0.06
     Parser
    0.06
    ważnie
    0.06
     أكثر
    0.06
     Disneyland
    0.06
    Act Density 0.000%

    No Known Activations