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

    Neuronpedia

    INDEX
    Explanations

    three

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    果园
    -0.07
    Ice
    -0.07
    condition
    -0.07
     Up
    -0.07
    Mexico
    -0.07
    市场上
    -0.06
    <ul
    -0.06
    体育投注
    -0.06
     TextStyle
    -0.06
     Crystal
    -0.06
    POSITIVE LOGITS
     empir
    0.07
     właśc
    0.07
    andid
    0.07
    Bid
    0.06
     владельц
    0.06
    保证
    0.06
     Ged
    0.06
     detainees
    0.06
     detained
    0.06
    .Arg
    0.06
    Act Density 0.001%

    No Known Activations