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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    우스
    -0.06
     meal
    -0.06
    chts
    -0.06
     occupy
    -0.06
     δι
    -0.06
    OUCH
    -0.06
    "M
    -0.06
     persist
    -0.06
     Minds
    -0.06
    ฟ
    -0.06
    POSITIVE LOGITS
    /*.
    0.07
     avatar
    0.07
    '>";↵
    0.06
    εται
    0.06
    uido
    0.06
    ()})↵
    0.06
     issuance
    0.06
     información
    0.06
    !!}↵
    0.06
    ธน
    0.06
    Act Density 0.018%

    No Known Activations