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

    Neuronpedia

    INDEX
    Explanations

    Forms of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caucasian
    -0.07
    arehouse
    -0.07
    merchant
    -0.07
     RAID
    -0.06
    ランキング
    -0.06
     soy
    -0.06
    瘭
    -0.06
     Palestin
    -0.06
    irth
    -0.06
    aram
    -0.06
    POSITIVE LOGITS
    此处
    0.07
    迹
    0.07
    跑了
    0.07
    一场
    0.07
     Fischer
    0.07
    owers
    0.07
    grounds
    0.07
    agr
    0.06
    力を
    0.06
     entity
    0.06
    Act Density 0.888%

    No Known Activations