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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    legate
    -0.06
    .NORTH
    -0.06
     bars
    -0.06
    gray
    -0.06
     WHITE
    -0.06
    σιμοποι
    -0.06
    (DEBUG
    -0.06
     NOT
    -0.06
    /K
    -0.06
    eking
    -0.06
    POSITIVE LOGITS
     Obesity
    0.07
     �
    0.06
     тщ
    0.06
    airro
    0.06
     미국
    0.06
     ucwords
    0.06
     대전
    0.06
     securities
    0.06
     Oscar
    0.06
    ...\
    0.06
    Act Density 0.008%

    No Known Activations