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

    Neuronpedia

    INDEX
    Explanations

    say "@app"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	id
    -0.07
     Brett
    -0.06
    11
    -0.06
    Para
    -0.06
     住
    -0.06
    _intensity
    -0.06
    Э
    -0.06
    から
    -0.06
    Im
    -0.06
    ";
    -0.06
    POSITIVE LOGITS
     économ
    0.07
    .banner
    0.07
     resemble
    0.06
     press
    0.06
    compact
    0.06
     brightness
    0.06
    PrimaryKey
    0.06
    -stock
    0.06
    廊
    0.06
    unction
    0.06
    Act Density 0.053%

    No Known Activations