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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Binary
    -0.07
    สมบ
    -0.07
    ивания
    -0.07
     amplify
    -0.06
     cafeteria
    -0.06
    人気
    -0.06
     pat
    -0.06
    abwe
    -0.06
    asonic
    -0.06
     YT
    -0.06
    POSITIVE LOGITS
    ”，
    0.07
    stdout
    0.07
    sed
    0.06
    ()>
    0.06
    -maker
    0.06
     |--
    0.06
    >_
    0.06
    ?),
    0.06
    roll
    0.06
    šil
    0.06
    Act Density 0.052%

    No Known Activations