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

    Neuronpedia

    INDEX
    Explanations

    Legal arguments/disputes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mar
    -0.06
    482
    -0.06
     licensing
    -0.06
    moved
    -0.06
     indicating
    -0.06
    686
    -0.06
    ')],↵
    -0.06
    ------------------------------------------------
    -0.06
    服务
    -0.06
    -training
    -0.06
    POSITIVE LOGITS
     daddy
    0.07
     cityName
    0.07
     путем
    0.07
    POST
    0.07
    duino
    0.06
    /pop
    0.06
    OPEN
    0.06
     Wolverine
    0.06
     металли
    0.06
    .MONTH
    0.06
    Act Density 0.029%

    No Known Activations