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

    Neuronpedia

    INDEX
    Explanations

    backpack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zhu
    -0.07
     Yue
    -0.07
     부
    -0.06
    Chinese
    -0.06
    _SM
    -0.06
     judiciary
    -0.06
     resides
    -0.06
     shard
    -0.06
    uilt
    -0.06
    roadcast
    -0.06
    POSITIVE LOGITS
     backpack
    0.10
     Backpack
    0.09
     back
    0.08
    pack
    0.08
     Countdown
    0.07
     Assault
    0.07
     ".↵
    0.07
     education
    0.06
    .normalized
    0.06
     passengers
    0.06
    Act Density 0.002%

    No Known Activations