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

    Neuronpedia

    INDEX
    Explanations

    Code and other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ming
    -0.08
     slight
    -0.07
    \Post
    -0.07
     Determin
    -0.07
     Lemon
    -0.07
    IMAL
    -0.06
     motives
    -0.06
    𝇠
    -0.06
    .option
    -0.06
    気になる
    -0.06
    POSITIVE LOGITS
    沤
    0.08
    近年
    0.07
    執
    0.07
    社保
    0.07
     argv
    0.07
     jq
    0.07
     ejec
    0.07
    Await
    0.07
     currentValue
    0.07
    ⇰
    0.07
    Act Density 0.001%

    No Known Activations