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

    Neuronpedia

    INDEX
    Explanations

    "there it was"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spre
    -0.08
    "]]
    -0.08
     Carbon
    -0.07
    추천
    -0.07
    registre
    -0.07
     informal
    -0.07
    carbon
    -0.07
    "]],↵
    -0.07
    िमाग
    -0.07
     recomendar
    -0.07
    POSITIVE LOGITS
    aturation
    0.08
    149
    0.08
     bring
    0.08
     dearly
    0.07
     blazing
    0.07
     cable
    0.07
     know
    0.07
     literally
    0.07
    ived
    0.07
     تعالیٰ
    0.07
    Act Density 0.001%

    No Known Activations