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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abr
    -0.07
    hões
    -0.07
     Ways
    -0.07
    xcc
    -0.07
    oğ
    -0.06
     <=
    -0.06
    íg
    -0.06
     computation
    -0.06
    냘
    -0.06
    },
↵
↵
    -0.06
    POSITIVE LOGITS
     touring
    0.07
    海报
    0.07
    .uid
    0.06
    让孩子
    0.06
     jewish
    0.06
    怖
    0.06
    איר
    0.06
     kter
    0.06
     swift
    0.06
    زوار
    0.06
    Act Density 0.001%

    No Known Activations