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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    explode
    -0.07
    ∾
    -0.07
     macOS
    -0.07
    .firebase
    -0.07
    :UI
    -0.07
    끕
    -0.06
    Ɩ
    -0.06
     Furn
    -0.06
    だけ
    -0.06
    🔒
    -0.06
    POSITIVE LOGITS
     dining
    0.07
    Ci
    0.07
     Ming
    0.07
     Fault
    0.06
    人民服务
    0.06
    ">';↵
    0.06
     Memo
    0.06
    @Service
    0.06
    enerima
    0.06
    Released
    0.06
    Act Density 0.058%

    No Known Activations