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

    Neuronpedia

    INDEX
    Explanations

    Things to avoid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enormously
    -0.08
     paddingLeft
    -0.07
     सच
    -0.07
     tremendously
    -0.07
     cannot
    -0.06
    capitalize
    -0.06
     आद
    -0.06
     getUser
    -0.06
    Temperature
    -0.06
     Pipe
    -0.06
    POSITIVE LOGITS
    ]["
    0.07
    .""
    0.07
    （笑
    0.07
    obel
    0.06
    igrations
    0.06
     cinco
    0.06
     přičemž
    0.06
    .CreateTable
    0.06
    asje
    0.06
    }})↵
    0.06
    Act Density 0.090%

    No Known Activations