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

    Neuronpedia

    INDEX
    Explanations

    drinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Directory
    -0.07
    alar
    -0.07
    <R
    -0.06
     CONNECT
    -0.06
    entions
    -0.06
     pencil
    -0.06
    _capture
    -0.06
     Damon
    -0.06
    Ark
    -0.06
    andest
    -0.06
    POSITIVE LOGITS
     ‫
    0.07
    Segment
    0.06
    ">
↵
↵
    0.06
    mort
    0.06
    /Dk
    0.06
    >`↵
    0.06
     Porter
    0.06
     Jaguars
    0.06
    인은
    0.06
    	ch
    0.06
    Act Density 0.008%

    No Known Activations