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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VIN
    -0.07
     patriot
    -0.07
     vary
    -0.06
    ume
    -0.06
     ok
    -0.06
    (ra
    -0.06
     satire
    -0.06
    docker
    -0.06
    ジア
    -0.06
     manga
    -0.06
    POSITIVE LOGITS
    年度
    0.08
    Administr
    0.07
    ">'.$
    0.07
     ऐस
    0.06
    #include
    0.06
    Inf
    0.06
     않을
    0.06
    �
    0.06
     InkWell
    0.06
    _blueprint
    0.06
    Act Density 0.130%

    No Known Activations