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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    遺
    -0.07
     untouched
    -0.07
     trophy
    -0.06
    เหม
    -0.06
     sure
    -0.06
     후
    -0.06
    相比于
    -0.06
     Steering
    -0.06
    挡
    -0.06
    켇
    -0.06
    POSITIVE LOGITS
    .parameters
    0.08
    urrection
    0.07
    ❥
    0.07
    rise
    0.07
    UITableViewCell
    0.07
    .tech
    0.07
    -growing
    0.07
    versations
    0.07
     Randall
    0.07
    (server
    0.07
    Act Density 0.006%

    No Known Activations