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

    Neuronpedia

    INDEX
    Explanations

    wrong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,err
    -0.06
     YAML
    -0.06
    :\"
    -0.06
    ylland
    -0.06
     librarian
    -0.06
    aptops
    -0.06
    .server
    -0.06
    embali
    -0.06
    ンバー
    -0.06
    ентами
    -0.06
    POSITIVE LOGITS
    astreet
    0.07
    /thumb
    0.07
    τω
    0.07
     preserves
    0.06
    rove
    0.06
     جن
    0.06
    ΑΤ
    0.06
     pounds
    0.06
    용
    0.06
     inté
    0.06
    Act Density 0.004%

    No Known Activations